commit 21152087d82a9db4523fcb52143c62e68d1e61c5 Author: ModelHub XC Date: Fri May 29 03:32:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: kakaocorp/kanana-1.5-15.7b-a3b-instruct Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..1d6566a --- /dev/null +++ b/LICENSE @@ -0,0 +1,73 @@ +KANANA LICENSE AGREEMENT + +Kanana Release Date: July 17, 2025 + +This KANANA LICENSE AGREEMENT (this “Agreement”) is made by and between you and Kakao Corp. (“KAKAO”) that governs your use of Kanana Materials that KAKAO provides to you. +By using, copying, modifying, distributing, performing, or displaying all or part of Kanana Materials, or otherwise accepting the terms and conditions of this Agreement, you agree to be bound by this Agreement. You hereby represent and warrant that (i) you are legally authorized to enter into this Agreement, and (ii) if you are entering into this Agreement on behalf of a legal entity, you have the authority to legally and validly bind such entity. + +1. Definition + 1.1 “Agreement” means the terms and conditions for use, copying, distribution and modification of Kanana Materials as set forth herein. + 1.2 “KAKAO” means Kakao Corp. + 1.3 “You” means an individual or legal entity that enters into this Agreement with KAKAO and exercises its rights hereunder or uses Kanana Materials for any purpose. If you enter into this Agreement on behalf of a legal entity, “you” shall include such entity. + 1.4 “Kanana” means the basic large-scale language model, software, and algorithms distributed by KAKAO under this Agreement, including parameters (such as Model Weights and optimizer status), machine learning model codes, inference/learning/fine-tuning codes, and other related elements. + 1.5 “Documentation” means the specifications, manuals, and other documentation accompanying Kanana distributed by KAKAO. + 1.6 “Kanana Materials” means, collectively, Kanana and Documentation, including any portions or components thereof. + 1.7 “Outputs” means information content generated by operating or otherwise using Kanana Materials. + 1.8 “Derivative Works” means (i) any modifications to Kanana, (ii) any work of authorship based on Kanana, or (iii) any other designed machine learning models that either directly use the patterns of Model Weights, parameters, operations, and/or outputs or incorporate a substantial part of Kanana’s performance or functional characteristics through methods including, but not limited to, transfer learning, fine-tuning, or knowledge distillation. This includes distillation methods using Kanana’s intermediate data representations or a method based on the synthetic data outputs generated by Kanana; provided, however, that Outputs shall not be deemed to be Derivative Works. + 1.9 “Model Weights” means a set of numerical parameter values generated during Kanana’s learning process, representing the result of substantial investment and effort by KAKAO. + +2. Grant of License and Use Policy + 2.1 Grant of License. Subject to the terms and conditions of this Agreement, you are granted a non-exclusive, worldwide, non-transferrable, royalty-free limited license under KAKAO’s intellectual property or other rights owned by KAKAO that enables you to access, download, install, copy, use, reproduce, distribute, create Derivative Works of, and make modifications to Kanana Materials. + 2.2 Policy on Prohibited Use. Your use of Kanana Materials and Derivative Works must comply with applicable laws and regulations and adhere to KAKAO’s Guidelines For Responsible AI (https://www.kakaocorp.com/page/responsible/detail/guidelinesForResponsibleAI), which is hereby incorporated into this Agreement. + 2.3 This Agreement applies solely to Kanana-*** and shall not apply to any other models distributed by KAKAO under separate licenses. Licenses applicable to such other models shall not apply to Kanana-***. + 2.4 The license terms applicable to a specific version of Kanana applies exclusively to that version and shall not extend to any other versions. Each version shall be deemed as an independent and separate work of authorship. + 2.5 You may use each version of Kanana only in accordance with the license terms expressly specified for that version, and you shall not claim that the license terms applicable to one version apply to any other version. + 2.6 You shall not combine different versions of Kanana versions that are subject to different license terms in order to circumvent any applicable license terms. + +3. Redistribution + 3.1 You may copy, distribute or disclose Kanana, Derivative Works, or any products or services that contain Kanana or Derivative Works; provided, however, that you shall: + (i) incorporate the compliance obligation set forth in the Policy on Prohibited Use provision of Section 2.2 in any agreement for use and distribution and notify subsequent users that such use restrictions apply; + (ii) provide any recipients of Kanana Materials or Derivative Works a copy of this Agreement; + (iii) expressly indicate in any files you have modified that it has been modified by you; + (iv) include a “Notice” text file that includes the following notice: + “Kanana is licensed in accordance with the Kanana License Agreement. Copyright © KAKAO Corp. All Rights Reserved.”; and + (v) clearly display the phrase “Powered by Kanana” on related websites, user interfaces, blog posts, introduction pages, or product documentation in a manner that is easily recognizable to users. In addition, if you use Kanana Materials or their outputs to create, train, improve, or enhance other AI models and distribute them, you must include ‘Kanana’ as a prefix to the name of such AI models. + 3.2 You may add your own copyright statement to your modifications of Kanana Materials and may provide additional or different license terms and conditions; provided, however, that such additional or different license terms and conditions shall not violate or conflict with any provisions of this Agreement. + +4. Additional Commercial Terms + 4.1 If you wish to engage in any of the following activities using Kanana Materials or any Derivative Works, you must obtain a separate commercial license expressly granted by KAKAO: + (i) Offering or (re)selling to third parties access to Kanana Materials or any Derivative Works through API, cloud platforms, or other remote access services; + (ii) Offering or (re)selling to third parties Kanana Materials or any Derivative Works in whole or in part, as part of a system integration (SI) or on-premise deployment solution; or + (iii) Offering or (re)selling to third parties Kanana Materials or any Derivative Works embedded in an on-device domains. + 4.2 If, as of Kanana Release Date, the number of monthly active users of the products or services provided by you and/or your affiliates, is greater than 10 million in the preceding calendar month, you must obtain a separate commercial license expressly granted by KAKAO. + 4.3 For clarity, unless your activities or conditions fall within those specified in Sections 4.1 and 4.2 above, you may use Kanana Materials or any Derivative Works for the development and operation of your own services without obtaining a commercial license from KAKAO. + 4.4 The grant of any commercial license under Sections 4.1 and 4.2 shall be at KAKAO’s sole discretion + +5. Outputs +KAKAO will not claim any rights to Outputs you generate using Kanana Materials. You shall be solely responsible for Outputs and the use thereof. + +6. Disclaimer of Warranty +Unless required by law, Kanana Materials are provided on an “AS IS” basis, and KAKAO disclaims all warranties of any kind, both express and implied, including, without limitation, any warranties of title, non-infringement, merchantability, or fitness for a particular purpose. + +7. Limitation on Liability +Unless required by law, in no event shall KAKAO be liable to you for damages, including any direct, indirect, special, consequential, incidental, and punitive damages of any character arising out of the use or inability to use Kanana Materials, Derivative Works, or Outputs, even if KAKAO has been advised of the possibility of such damages. + +8. Indemnification +You shall indemnify and hold KAKAO harmless from and against any and all claims that may be filed by a third party as a result of your infringement of any third party’s rights or violation of any applicable law, to the extent caused by your use or distribution of Kanana Materials, Derivative Works, or Outputs; provided, however, that the foregoing shall not apply to claims resulting from KAKAO’s willful or gross negligence. + +9. Intellectual Property + 9.1 This Agreement does not grant you any rights to use KAKAO’s trademarks, service marks, or product names. However, on a limited basis and solely for the purpose of complying with Section 3.1(v), KAKAO authorizes you to use the Kanana trademark, provided that KAKAO may require you to discontinue such use at any time if you impair the value of the Kanana trademark. + 9.2 KAKAO retains ownership of Kanana Materials and Derivative Works created by KAKAO, but you will retain ownership of any Derivative Works and modifications made by you. + 9.3 If you bring any legal action or proceeding against KAKAO or a third party alleging that the Kanana Materials, Derivative Works, or Outputs infringe your intellectual property rights, your rights under this Agreement shall automatically terminate as of the date such action is filed. + 9.4 You acknowledge that Model Weights are a valuable asset of KAKAO. You shall not extract, copy, distribute, modify Model Weights or use them to train new models, except as expressly permitted under this Agreement. + 9.5 The protections under this Agreement apply to all components of Kanana Materials (irrespective of whether it is recognized as a work of authorship), including, but not limited to, Model Weights, parameters, algorithms, or structures. You may exercise your rights in these components only to the extent expressly permitted under this Agreement. + +10. Term and Termination +The term of this Agreement will commence upon your acceptance of this Agreement or access to Kanana Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. KAKAO may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of Kanana Materials and Derivative Works. Sections 5, 6, 7, 8, 10 and 11 shall survive the termination of this Agreement. + +11. Governing Law and Arbitration + 11.1 This Agreement will be governed and construed under the laws of the Republic of Korea, without regard to its conflicts of laws principles. + 11.2 Any disputes arising out of or in connection with this Agreement shall be finally settled by arbitration in accordance with the International Arbitration Rules of the Korean Commercial Arbitration Board. The number of arbitrators shall be one. The seat, or legal place, of arbitral proceedings shall be Seoul, Republic of Korea. The language to be used in the arbitral proceedings shall be English. Either party may seek interim or provisional relief from a court of competent jurisdiction, which shall not be considered a waiver of any provision in this Section. The arbitral tribunal also has the authority to issue orders for interim or provisional relief. + +12. No Waiver +KAKAO’s failure or delay in exercising any of its rights under this Agreement shall not constitute a waiver of such rights. \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f4255be --- /dev/null +++ b/README.md @@ -0,0 +1,238 @@ +--- +language: +- en +- ko +library_name: transformers +license: other +license_name: "kanana" +license_link: LICENSE +pipeline_tag: text-generation +model_id: kakaocorp/kanana-1.5-15.7b-a3b-instruct +repo: kakaocorp/kanana-1.5-15.7b-a3b-instruct +developers: Kanana LLM +training_regime: bf16 mixed precision +--- + +

+
+ + + +
+ +

+🤗 1.5 HF Models   | +  📕 Kanana-1.5-15.7B-A3B Blog   + +
+ +## News 🔥 + +- ✨`2025/07/24`: Published a [blog post](https://tech.kakao.com/posts/716) about `Kanana-1.5-15.7B-A3B` models and released 🤗[HF model weights](https://kko.kakao.com/kananallm). +- 📕`2025/05/23`: Published a [blog post](https://tech.kakao.com/posts/707) about `Kanana 1.5` models and released 🤗[HF model weights](https://kko.kakao.com/kananallm). +- 📜`2025/02/27`: Released [Technical Report](https://arxiv.org/abs/2502.18934) and 🤗[HF model weights](https://huggingface.co/collections/kakaocorp/kanana-nano-21b-67a326cda1c449c8d4172259). +- 📕`2025/01/10`: Published a [blog post](https://tech.kakao.com/posts/682) about the development of `Kanana Nano` model. +- 📕`2024/11/14`: Published blog posts ([pre-training](https://tech.kakao.com/posts/661), [post-training](https://tech.kakao.com/posts/662)) about the development of `Kanana` models. +- ▶️`2024/11/06`: Published a [presentation video](https://youtu.be/HTBl142x9GI?si=o_we6t9suYK8DfX3) about the development of the `Kanana` models. + +
+ +## Table of Contents + +- [Kanana-1.5-15.7B-A3B](#kanana-15-157b-a3b) + - [Performance](#performance) + - [Base Model Evaluation](#base-model-evaluation) + - [Instruct Model Evaluation](#instruct-model-evaluation) +- [Contributors](#contributors) +- [Citation](#citation) +- [Contact](#contact) + +
+ +# Kanana-1.5-15.7B-A3B + +Introducing `Kanana-1.5-15.7B-A3B`, the first Mixture-of-Experts (MoE) model in our Kanana family, engineered for exceptional efficiency and powerful performance. `Kanana-1.5-15.7B-A3B`, which has sparse architecture, delivers capabilities comparable to the `Kanana-1.5-8B` dense model while utilizing only 37% of the FLOPS per token, making it a highly inference-efficient and cost-effective solution for real-world applications. Furthermore, `Kanana-1.5-15.7B-A3B` is powered by our newly enhanced post-training strategy, which includes on-policy distillation followed by reinforcement learning. + +> [!Note] +> Neither the pre-training nor the post-training data includes Kakao user data. + +## Performance + +### Base Model Evaluation + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelsMMLUKMMLUHAERAEHumanEvalMBPPGSM8K
Kanana-1.5-15.7B-A3B64.7951.7783.2359.7660.1061.18
Kanana-1.5-8B64.2448.9482.7761.5957.8063.53
Kanana-1.5-3B*59.2347.3078.0046.3446.8061.79
+ +
+ +### Instruct Model Evaluation + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelsMT-BenchKoMT-BenchIFEvalHumanEval+MBPP+GSM8K (0-shot)MATHMMLU (0-shot, CoT)KMMLU (0-shot, CoT)
Kanana-1.5-15.7B-A3B7.677.2473.3579.2770.3783.0266.4268.5548.92
Kanana-1.5-8B7.767.6380.1176.8367.9987.6467.5468.8248.28
Kanana-1.5-3B*7.016.5270.0870.7364.2980.3656.7059.6937.60
+ +> [!Note] +> \* This model is not an open-sourced, just for comparison with Kanana-1.5-15.7B-A3B + +
+ +### Evaluation Protocol +- Base Model Benchmarks + - MMLU, KMMLU, HAE-RAE: 5-shot, log-likelihood + - HumanEval: 0-shot, pass@1 + - MBPP: 3-shot, pass@1 + - GSM8K: 5-shot, exact-match (strict-match) + +- Instruct Model Benchmarks + - MT-Bench, KoMT-Bench: 0-shot, gpt-4o-2024-08-06 as judge model + - IFEval: 0-shot, mean of strict-prompt-level and strict-instruction-level + - HumanEval+, MBPP+: 0-shot, pass@1 + - GSM8K, MATH: 0-shot, rule-based verification + +
+ +## Quickstart + +### vLLM +- `vllm>=0.8.5` or the latest version is required to run `Kanana` model. + +#### Example Usage for `Kanana-1.5-15.7B-A3B-Instruct` +```bash +vllm serve $path_to_model \ + --served_model_name kanana-1.5-15.7b-a3b-instruct \ + --max-model-len 32768 \ + --gpu-memory-utilization 0.9 \ + --port 8000 \ + --dtype auto \ + --disable_cascade_attn \ + --tool-parser-plugin kanana_tool_calls/functionary_kanana_tool_parser.py \ + --tool-call-parser functionary_v3_llama_31 \ + --enable-auto-tool-choice \ + --chat-template kanana_tool_calls/lmalign_v1.jinja + +curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{ + "model": "kanana-1.5-15.7b-a3b-instruct", + "messages": [ + {"role": "system", "content": "You are a helpful AI assistant developed by Kakao."}, + {"role": "user", "content": "Explain LLM to a 5-year-old child in two simple sentences."} + ], + "top_k": 1, + "max_tokens": 72 +}' + +# Output: +''' +... +"choices":[{"index":0,"message":{"role":"assistant","content":"Sure! Imagine you have a super smart friend who can read and understand lots of books, talk to you in many different languages, and even help you with your homework. That is kind of like a Large Language Model (LLM) - it is a special computer friend that can do many cool things with words!" ... +... +''' +``` + +
+ +## Contributors +- Language Model Training + - Yunju Bak, Doohae Jung, Boseop Kim, Nayeon Kim, Hojin Lee, Jaesun Park, Minho Ryu, Jiyeon Ham, Seungjae Jung, Hyunho Kim, Hyunwoong Ko, Changmin Lee, Taegyeong Eo + +
+ +## Citation + +``` +@misc{kananallmteam2025kananacomputeefficientbilinguallanguage, + title={Kanana: Compute-efficient Bilingual Language Models}, + author={Kanana LLM Team and Yunju Bak and Hojin Lee and Minho Ryu and Jiyeon Ham and Seungjae Jung and Daniel Wontae Nam and Taegyeong Eo and Donghun Lee and Doohae Jung and Boseop Kim and Nayeon Kim and Jaesun Park and Hyunho Kim and Hyunwoong Ko and Changmin Lee and Kyoung-Woon On and Seulye Baeg and Junrae Cho and Sunghee Jung and Jieun Kang and EungGyun Kim and Eunhwa Kim and Byeongil Ko and Daniel Lee and Minchul Lee and Miok Lee and Shinbok Lee and Gaeun Seo}, + year={2025}, + eprint={2502.18934}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2502.18934}, +} +``` + +
+ +## Contact +- Kanana LLM Team Technical Support: kanana-llm@kakaocorp.com +- Business & Partnership Contact: alpha.k@kakaocorp.com \ No newline at end of file diff --git a/assets/logo/kanana-logo.png b/assets/logo/kanana-logo.png new file mode 100644 index 0000000..e446d47 Binary files /dev/null and b/assets/logo/kanana-logo.png differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..1898332 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128009, + 128256 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 1152, + "max_position_embeddings": 32768, + "model_type": "mixtral", + "num_attention_heads": 32, + "num_experts_per_tok": 8, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "num_local_experts": 64, + "output_router_logits": false, + "pad_token_id": 128001, + "rms_norm_eps": 1e-05, + "rope_theta": 16000000.0, + "router_aux_loss_coef": 0.005, + "router_jitter_noise": 0.0, + "scoring_func": "softmax", + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.1", + "use_cache": true, + "vocab_size": 128259 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6c90e66 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": [ + 128009, + 128256 + ], + "pad_token_id": 128001, + "transformers_version": "4.51.1" +} diff --git a/kanana_tool_calls/__pycache__/functionary_kanana_tool_parser.cpython-310.pyc b/kanana_tool_calls/__pycache__/functionary_kanana_tool_parser.cpython-310.pyc new file mode 100644 index 0000000..4c95b95 Binary files /dev/null and b/kanana_tool_calls/__pycache__/functionary_kanana_tool_parser.cpython-310.pyc differ diff --git a/kanana_tool_calls/__pycache__/functionary_kanana_tool_parser.cpython-312.pyc b/kanana_tool_calls/__pycache__/functionary_kanana_tool_parser.cpython-312.pyc new file mode 100644 index 0000000..802b96f Binary files /dev/null and b/kanana_tool_calls/__pycache__/functionary_kanana_tool_parser.cpython-312.pyc differ diff --git a/kanana_tool_calls/functionary_kanana_tool_parser.py b/kanana_tool_calls/functionary_kanana_tool_parser.py new file mode 100644 index 0000000..2f7882d --- /dev/null +++ b/kanana_tool_calls/functionary_kanana_tool_parser.py @@ -0,0 +1,401 @@ +import json +from json import JSONDecodeError, JSONDecoder +import copy +import uuid +from pathlib import Path +from typing import Dict, List, Optional, Union, Sequence +from abc import ABC, abstractmethod + +import partial_json_parser +from partial_json_parser.core.options import Allow + +from transformers import PreTrainedTokenizerBase +from vllm.entrypoints.openai.protocol import ( + ChatCompletionRequest, + ExtractedToolCallInformation, + DeltaMessage, + DeltaFunctionCall, + DeltaToolCall +) +from vllm.entrypoints.openai.tool_parsers.abstract_tool_parser import ToolParser, ToolParserManager +from vllm.entrypoints.openai.tool_parsers.utils import find_common_prefix +from vllm.logger import init_logger +from vllm.utils import random_uuid +from vllm.transformers_utils.tokenizer import AnyTokenizer + + + +from transformers import PreTrainedTokenizer + + +logger = init_logger(__name__) + + + +class BaseTemplate(ABC): + @abstractmethod + def response_to_messages(self, generated_text): + raise NotImplementedError + +class FunctionaryV3Llama31Template(BaseTemplate): + def __init__( + self, + tokenizer: PreTrainedTokenizer + ): + self.tokenizer = tokenizer + + self.system_tokens = "<|start_header_id|>system<|end_header_id|>\n\n" + self.user_tokens = "<|start_header_id|>user<|end_header_id|>\n\n" + self.assistant_tokens = "<|start_header_id|>assistant<|end_header_id|>\n\n" + self.tool_tokens = "<|start_header_id|>ipython<|end_header_id|>\n\n" + + def parse_function_call_from_text(self, function_call_text: str) -> Optional[Dict]: + index = function_call_text.find(">") + if index >= 0: + func_name = function_call_text[:index].strip() + arguments = function_call_text[index + 1:].strip() + return {"name": func_name, "arguments": arguments} + return None + + def response_to_messages(self, generated_text): + # first remove stop tokens if there exists + for stop in [self.tokenizer.eos_token, "<|eom_id|>", "<|end_of_text|>"]: + if generated_text.endswith(stop): + generated_text = generated_text[: -len(stop)] + + tool_calls = [] + text_response = "" + + func_prefix = " 0: + if generated_text.startswith(python_tag): # check if use code interpreter + code = generated_text[len(python_tag) :] + function_call = { + "name": "python", + "arguments": code, + } + + tool_calls.append( + { + "type": "function", + "id": str(uuid.uuid4()), + "function": function_call, + } + ) + generated_text = "" + elif generated_text.startswith(func_prefix): # Check if function_call + end_index = generated_text.find(end_func) + if end_index >= 0: + function_call_text = generated_text[len(func_prefix) : end_index] + function_call = self.parse_function_call_from_text(function_call_text) + + tool_calls.append( + { + "type": "function", + "id": str(uuid.uuid4()), + "function": function_call, + } + ) + generated_text = generated_text[end_index + len(end_func) :] + else: + # TODO cannot find close function call + text_response += generated_text + break + else: # If text-response + text_response += generated_text[0] + generated_text = generated_text[1:] + + if not text_response: + text_response = None + elif len(text_response.strip()) == 0: + text_response = None + + if not tool_calls: + tool_calls = None + + if tool_calls: + return {"role": "assistant", "content": text_response, "tool_calls": tool_calls} + else: + return {"role": "assistant", "content": text_response} + + + +# partial_json_parser doesn't support extra data and +# JSONDecorder.raw_decode doesn't support partial JSON +def partial_json_loads(input_str, flags): + try: + return partial_json_parser.loads(input_str, flags), len(input_str) + except JSONDecodeError as e: + if "Extra data" in e.msg: + dec = JSONDecoder() + return dec.raw_decode(input_str) + else: + raise + + +def is_complete_json(input_str): + try: + json.loads(input_str) + return True + except JSONDecodeError: + return False + +@ToolParserManager.register_module(["functionary_v3_llama_31"]) +class FunctionaryV3Llama31ToolParser(ToolParser): + def __init__(self, tokenizer: Union[PreTrainedTokenizerBase, AnyTokenizer]): + super().__init__(tokenizer) + self.template = FunctionaryV3Llama31Template(tokenizer=tokenizer) + + self._func_prefix = " ExtractedToolCallInformation: + result = self.template.response_to_messages(model_output) + if "tool_calls" in result: + return ExtractedToolCallInformation(tools_called=True, + tool_calls=result["tool_calls"], + content=None) + else: + return ExtractedToolCallInformation(tools_called=False, + tool_calls=[], + content=result["content"]) + + # our template: {"arg":"var"} + def extract_tool_calls_streaming( + self, + previous_text: str, + current_text: str, + delta_text: str, + previous_token_ids: Sequence[int], + current_token_ids: Sequence[int], + delta_token_ids: Sequence[int], + request: ChatCompletionRequest, + ) -> Union[DeltaMessage, None]: + + # if current_text does not start with function tag (or python tag), + if not (current_text.startswith(self._python_tag) + or current_text.startswith(self._func_prefix) + or self._func_prefix.startswith(current_text)): + # for cases like "The answer is + for stop in [self.eos_token, "<|eom_id|>", "<|end_of_text|>"]: + if current_text.rstrip().endswith(stop): + current_text = current_text.rstrip()[: -len(stop)] + + # if current_tool_name is not sent yet, + # don't allow partial sending of strings + # (supposedly, openai also only sends the entire tool name at once) + # not really relevant to kanana + flags = Allow.ALL if self.current_tool_name_sent \ + else Allow.ALL & ~Allow.STR + + try: + tool_call_arr = [] + is_complete = [] + obj = {} + try: + # set start_idx + start_idx = 0 + while start_idx < len(current_text): + name = None + # set function_name and move start_idx to the end of function_name + if current_text[start_idx:].startswith(self._python_tag): + name = "python" + start_idx += len(self._python_tag) + elif current_text[start_idx:].startswith(self._func_prefix): + idx = current_text[start_idx:].find(">") + # found ">" which means function name is ready + if idx != -1: + function_name = current_text[start_idx+len(self._func_prefix):start_idx+idx] + name = function_name + start_idx += len(self._func_prefix) + len(function_name) + len(">") + # for cases like: abcd and , which declares the end of a function, + # move start_idx to the end so it can skip + function_end_idx = current_text[start_idx:].find(self._func_suffix) + if function_end_idx != -1: + start_idx += len(self._func_suffix) + # if hasn't been generated fully yet, + # but the function is complete, we break out from while loop + # and stream it right away + elif is_complete[-1]: + break + except partial_json_parser.core.exceptions.MalformedJSON: + logger.debug('not enough tokens to parse into JSON yet') + return None + + # current_tool_call is the one that is being streamed + current_tool_call: dict = tool_call_arr[self.current_tool_id] \ + if len(tool_call_arr) > 0 else {} + + # case0: if there is no tool call in the array, return None + if len(tool_call_arr) == 0: + return None + + # case1: we are starting a new tool in the array + # -> tool_call_arr has > 0 length AND has more elements than cursor + elif (len(tool_call_arr) > 0 + and len(tool_call_arr) > self.current_tool_id + 1): + # if we're moving on to a new call, first make sure we + # haven't missed anything in the previous one that was + # auto-generated due to JSON completions, but wasn't + # streamed to the client yet. + # print("starting a new tool in the array, print remaining") + if self.current_tool_id >= 0: + cur_arguments = current_tool_call.get("arguments") + if cur_arguments: + cur_args_json = json.dumps(cur_arguments, ensure_ascii=False) + sent = len( + self.streamed_args_for_tool[self.current_tool_id]) # streamed args for current tool call + argument_diff = cur_args_json[sent:] # args not yet streamed for current tool call + + logger.debug("got arguments diff: %s", argument_diff) + delta = DeltaMessage(tool_calls=[ + DeltaToolCall(index=self.current_tool_id, + function=DeltaFunctionCall( + arguments=argument_diff). + model_dump(exclude_none=True)) + ]) + self.streamed_args_for_tool[ + self.current_tool_id] += argument_diff # update streamed args for current tool call + else: + delta = None + else: + delta = None + # re-set stuff pertaining to progress in the current tool + self.current_tool_id = len(tool_call_arr) - 1 # update current tool call + self.current_tool_name_sent = False + self.streamed_args_for_tool.append("") + logger.debug("starting on new tool %d", self.current_tool_id) + return delta + + # case2: if the current tool name hasn't been sent, send if available + elif not self.current_tool_name_sent: + function_name = current_tool_call.get("name") + if function_name: + delta = DeltaMessage(tool_calls=[ + DeltaToolCall(index=self.current_tool_id, + type="function", + id=f"chatcmpl-tool-{random_uuid()}", + function=DeltaFunctionCall( + name=function_name).model_dump( + exclude_none=True)) + ]) + self.current_tool_name_sent = True + else: + delta = None + + # case3: now we know we're on the same tool call + # and can stream arguments + else: + cur_arguments = current_tool_call.get("arguments") + delta = None + # '{}' 인경우도 출력 해야함. + sent = len( + self.streamed_args_for_tool[self.current_tool_id]) # streamed args for current tool call + cur_args_json = json.dumps(cur_arguments, ensure_ascii=False) + prev_arguments = self.prev_tool_call_arr[ + self.current_tool_id].get("arguments") + argument_diff = None + # if current tool call is complete + if is_complete[self.current_tool_id]: + argument_diff = cur_args_json[sent:] + # if current tool call is not complete and prev_arguments exists + elif prev_arguments: + prev_args_json = json.dumps(prev_arguments, ensure_ascii=False) + if cur_args_json != prev_args_json: + # common prefix betwn prev and current args + prefix = find_common_prefix( + prev_args_json, cur_args_json) + argument_diff = prefix[sent:] + if argument_diff is not None and len(argument_diff) > 0: + delta = DeltaMessage(tool_calls=[ + DeltaToolCall(index=self.current_tool_id, + function=DeltaFunctionCall( + arguments=argument_diff). + model_dump(exclude_none=True)) + ]) + + self.streamed_args_for_tool[ + self.current_tool_id] += argument_diff + # update previous tool call array + self.prev_tool_call_arr = tool_call_arr + return delta + + except Exception as e: + logger.exception("Error trying to handle streaming tool call.") + logger.debug( + "Skipping chunk as a result of tool streaming extraction " + "error") + return None diff --git a/kanana_tool_calls/lmalign_v1.jinja b/kanana_tool_calls/lmalign_v1.jinja new file mode 100644 index 0000000..0afc386 --- /dev/null +++ b/kanana_tool_calls/lmalign_v1.jinja @@ -0,0 +1,320 @@ +{# version=v3-llama3.1 #}{%- macro append_new_param_info(param_declaration, comment_info, examples_info, depth) -%} + {%- set offset = "" -%} + {%- if depth >= 1 -%} + {%- set offset = " " * depth -%} + {%- endif -%} + {%- if comment_info != "<|NONE|>" -%} + {{ "\n" + offset + comment_info }} + {%- if examples_info | length > 0 -%} + {# Append each example info #} + {%- for example in examples_info -%} + {{ "\n" + offset + "// " + example|string|replace("'", '"') }} + {%- endfor -%} + {%- endif -%} + {%- endif -%} + {{ "\n" + offset + param_declaration }} +{%- endmacro -%} + +{%- macro convert_data_type(param_type) -%} + {%- if param_type == "integer" or param_type == "float" -%} + {{ "number" }} + {%- else -%} + {{ param_type }} + {%- endif -%} +{%- endmacro -%} + +{%- macro get_param_type(param) -%} + {%- set param_type = "any" -%} + + {%- if "type" in param -%} + {%- set raw_param_type = param["type"] -%} + {%- if raw_param_type is iterable and raw_param_type is not string -%} + {%- set param_type = raw_param_type | join(" | ") -%} + {%- else -%} + {%- set param_type = raw_param_type -%} + {%- endif -%} + {{ convert_data_type(param_type) }} + {%- elif "oneOf" in param -%} + {%- set one_of_types = param["oneOf"]|selectattr("type", "defined")|list -%} + {%- set one_of_types = one_of_types|map(attribute="type")|unique|list -%} + {{ convert_data_type(one_of_types | join(" | ")) }} + {%- endif -%} +{%- endmacro -%} + +{%- macro get_format_param(param) -%} + {%- if "format" in param -%} + {{ param["format"] }} + {%- elif "oneOf" in param -%} + {%- set formats = [] -%} + {%- for item in param["oneOf"] -%} + {%- if "format" in item -%} + {%- if item["format"] == param["oneOf"][-1]["format"] -%} + {{ item["format"] }} + {%- else -%} + {{ item["format"] + " or "}} + {%- endif -%} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ "<|NONE|>" }} + {%- endif -%} +{%- endmacro -%} + +{%- macro get_param_info(param) -%} + {%- set param_type = param.get("type", "any") -%} + {%- set format_param = get_format_param(param) -%} + + {%- if "description" in param or "default" in param or format_param != "<|NONE|>" or param["maximum"] or param["minimum"] or param["maxLength"] or param["minLength"] -%} + {{ "//" }} + {%- if "description" in param -%} + {%- set desc = param["description"] -%} + {%- if not desc.endswith(".") -%} + {%- set desc = desc + "." -%} + {%- endif -%} + {{ " " + desc }} + {%- endif -%} + + {%- if "default" in param -%} + {%- set default_value = param["default"] -%} + {%- if param_type == "string" -%} + {%- set default_value = '"' ~ default_value ~ '"' -%} + {%- endif -%} + {{ " Default=" ~ default_value ~ "." }} + {%- endif -%} + + {%- set format_param = get_format_param(param) -%} + {%- if format_param != "<|NONE|>" -%} + {{ " Format=" ~ format_param }} + {%- endif -%} + + {%- for field, field_name in [("maximum", "Maximum"), ("minimum", "Minimum"), ("maxLength", "Maximum length"), ("minLength", "Minimum length")] -%} + {%- if field in param -%} + {{ " " + field_name ~ "=" ~ param[field] }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ "<|NONE|>"}} + {%- endif -%} +{%- endmacro -%} + +{%- macro get_enum_option_str(enum_options) -%} + {%- for v in enum_options -%} + {%- if v is string -%} + {{ '"' + v + '"' }} + {%- else -%} + {{ v }} + {%- endif -%} + {%- if enum_options|length > 0 and v != enum_options[-1] -%} + {{ " | " }} + {%- endif -%} + {%- endfor -%} +{%- endmacro -%} + +{%- macro get_array_typescript(param_name, param_dic, depth) -%} + {%- set offset = '' -%} + {%- if depth >= 1 -%} + {%- set offset = " " * depth -%} + {%- endif -%} + {%- set items_info = param_dic.get('items', {}) -%} + + {%- if items_info|length == 0 -%} + {%- if param_name -%} + {{ "\n" + offset + param_name + ": []" }} + {%- else -%} + {{ "\n" + offset + "[]" }} + {%- endif -%} + {%- else -%} + {%- set array_type = get_param_type(items_info) -%} + {%- if array_type == 'object' -%} + {%- if param_name -%} + {{ "\n" + offset + param_name + ": {" }} + {%- else -%} + {{ "\n" + offset + "{" }} + {%- endif -%} + {{ get_parameter_typescript(items_info.get('properties', {}), items_info.get('required', []), depth + 1) -}} + {{- "\n" + offset + "}[]" }} + {%- elif array_type == 'array' -%} + {%- set item_info = get_array_typescript(None, items_info, depth + 1) -%} + {%- if not param_name -%} + {{ "\n" + item_info + "[]" }} + {%- else -%} + {{ "\n" + offset + param_name + ": " + item_info|trim + "[]" }} + {%- endif -%} + {%- else -%} + {%- if 'enum' in items_info -%} + {%- set item_type = get_enum_option_str(items_info['enum']) -%} + {%- if param_name is none -%} + {{ "(" + item_type + ")[]"}} + {%- else -%} + {{ "\n" + offset + param_name + ": (" + item_type + ")[]" }} + {%- endif -%} + {%- else -%} + {%- if param_name is none -%} + {{ "\n" + array_type + "[]" }} + {%- else -%} + {{ "\n" + offset + param_name + ": " + array_type + "[]," }} + {%- endif -%} + {%- endif -%} + {%- endif -%} + {%- endif -%} +{%- endmacro -%} + +{%- macro get_parameter_typescript(properties, required_params, depth=0) -%} + {%- set res = "" -%} + {%- for param_name, param in properties.items() -%} + {%- if param is mapping -%} + {%- set comment_info = get_param_info(param) -%} + {# Param Examples #} + {%- set examples_info = [] -%} + {%- if "examples" in param -%} + {%- set examples_info = ["Example " + param_name + ":"] -%} + {%- set examples_info = examples_info + param["examples"] -%} + {%- endif -%} + + {# Param Name declaration #} + {%- set param_declaration = param_name -%} + {%- if required_params is iterable and param_name not in required_params -%} + {%- set param_declaration = param_declaration + "?" -%} + {%- endif -%} + + {%- set param_type = get_param_type(param) -%} + + {# Handle indentation based on depth #} + {%- set offset = "" -%} + {%- if depth >= 1 -%} + {%- set offset = " " * depth -%} + {%- endif -%} + + {%- if param_type == "object" -%} + {%- if comment_info != "<|NONE|>" -%} + {{ "\n" + offset + comment_info }} + {%- endif -%} + {%- if examples_info|length > 0 -%} + {%- for example in examples_info -%} + {{ "\n" + offset + "// " + example|string|replace("'", '"') }} + {%- endfor -%} + {%- endif -%} + {%- set param_declaration = param_declaration + ": {" -%} + {{ "\n" + offset + param_declaration -}} + {{- get_parameter_typescript(param.get("properties", {}), param.get("required", []), depth + 1) -}} + {{- "\n" + offset + "}," }} + {%- elif param_type == "array" -%} + {%- set item_info = param.get("items", {}) -%} + {%- if "type" not in item_info -%} + {%- set param_declaration = param_declaration + ": []," -%} + {{ append_new_param_info(param_declaration, comment_info, examples_info, depth) }} + {%- else -%} + {%- if comment_info != "<|NONE|>" -%} + {{ "\n" + offset + comment_info }} + {%- endif -%} + {%- if examples_info|length > 0 -%} + {%- for example in examples_info -%} + {{ "\n" + offset + "// " + example|string|replace("'", '"') }} + {%- endfor -%} + {%- endif -%} + {%- set array_declaration = get_array_typescript(param_declaration, param, depth) -%} + {%- if not array_declaration.endswith(",") -%} + {%- set array_declaration = array_declaration + "," -%} + {%- endif -%} + {{ array_declaration}} + {%- endif -%} + {%- else -%} + {%- if "enum" in param -%} + {%- set param_type = get_enum_option_str(param["enum"]) -%} + {%- endif -%} + {%- if "nullable" in param and param["nullable"] -%} + {%- set param_type = param_type + " | null" -%} + {%- endif -%} + {%- set param_declaration = param_declaration + ": " + param_type + "," -%} + {{ append_new_param_info(param_declaration, comment_info, examples_info, depth) }} + {%- endif -%} + {%- endif -%} + {%- endfor -%} +{%- endmacro -%} + +{%- macro generate_schema_from_functions(functions, namespace='functions') -%} + {{ "// Supported function definitions that should be called when necessary.\n" -}} + {{- "namespace " + namespace + " {\n\n" -}} + + {%- for function in functions -%} + {%- if function.get("function") -%} + {%- set function = function.get("function") -%} + {%- endif -%} + + {%- set function_name = function.get("name") -%} + {%- if function_name -%} + {%- set description = function.get('description', '') -%} + {%- set parameters = function.get('parameters', {}) -%} + {{- "// " + description + "\n" -}} + {{- "type " + function_name -}} + {%- if parameters and parameters.get("properties") -%} + {{- " = (_: {" -}} + {%- set required_params = parameters.get("required", []) -%} + {{ get_parameter_typescript(parameters.get("properties"), required_params, 0) -}} + {{- "\n}) => any;\n\n" }} + {%- else -%} + {{ " = () => any;\n\n" }} + {%- endif -%} + {%- endif -%} + {%- endfor -%} + {{ "} // namespace " + namespace }} +{%- endmacro -%} +{%- if not tools is defined -%} + {%- set tools = none -%} +{%- endif -%} + +{%- set has_code_interpreter = tools | selectattr("type", "equalto", "code_interpreter") | list | length > 0 -%} +{%- if has_code_interpreter -%} + {%- set tools = tools | rejectattr("type", "equalto", "code_interpreter") | list -%} +{%- endif -%} + +{#- System message + builtin tools #} +{{- bos_token + "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if has_code_interpreter %} + {{- "Environment: ipython\n\n" }} +{%- else -%} + {{ "\n"}} +{%- endif %} +{%- if tools %} + {{- "\nYou have access to the following functions:\n\n" }} + {%- for t in tools %} + {%- if "type" in t -%} + {{ "Use the function '" + t["function"]["name"] + "' to '" + t["function"]["description"] + "'\n" + t["function"] | tojson() }} + {%- else -%} + {{ "Use the function '" + t["name"] + "' to '" + t["description"] + "'\n" + t | tojson }} + {%- endif -%} + {{- "\n\n" }} + {%- endfor %} + {{- '\nThink very carefully before calling functions.\nIf a you choose to call a function ONLY reply in the following format:\n<{start_tag}={function_name}>{parameters}{end_tag}\nwhere\n\nstart_tag => ` a JSON dict with the function argument name as key and function argument value as value.\nend_tag => ``\n\nHere is an example,\n{"example_name": "example_value"}\n\nReminder:\n- If looking for real time information use relevant functions before falling back to brave_search\n- Function calls MUST follow the specified format, start with \n- Required parameters MUST be specified\n- Only call one function at a time\n- Put the entire function call reply on one line\n\n' -}} +{%- endif %} +{{- "<|eot_id|>" -}} + +{%- for message in messages -%} + {%- if message['role'] == 'user' or message['role'] == 'system' -%} + {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] + '<|eot_id|>' }} + {%- elif message['role'] == 'tool' -%} + {{ '<|start_header_id|>ipython<|end_header_id|>\n\n' + message['content'] + '<|eot_id|>' }} + {%- else -%} + {%- if (message['content'] and message['content']|length > 0) or ('tool_calls' in message and message['tool_calls'] and message['tool_calls']|length > 0) -%} + {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'}} + {%- endif -%} + {%- if message['content'] and message['content']|length > 0 -%} + {{ message['content'] }} + {%- endif -%} + {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls']|length > 0 -%} + {%- for tool_call in message['tool_calls'] -%} + {%- if tool_call["function"]["name"] == "python" -%} + {{ '<|python_tag|>' + tool_call['function']['arguments']|tojson }} + {%- else -%} + {{ '' + tool_call['function']['arguments']|tojson + '' }} + {%- endif -%} + {%- endfor -%} + {{ '<|eom_id|>' }} + {%- elif message['content'] and message['content']|length > 0 -%} + {{ '<|eot_id|>' }} + {%- endif -%} + {%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif -%} diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..8950825 --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dad6208f73ba0cc3888e79b00cca1e1cda31918e7eaa54d4817434fb65e9752 +size 4996655056 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..0b6c1af --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe55eb0566228b34a8048e27ac87be1c3e40707332a9aed5dc20f706b18ed2b8 +size 4996387760 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..c08628e --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5702b956fc53c7794a5ea02c2970ce8f04c74a1df6d30680f0aa6aba0a8f8c9 +size 4997955960 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..845604e --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9028ffca029922250bef1ae796c5dd92ced54c06b1b0928250f0f5884afad0a4 +size 4996092176 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..8597024 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9169539b4dba1bb628cba22b414664da537aeb497188a7858b9deb6fcf7183ba +size 4996096824 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..33d93c0 --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe57c4eafa292e8cc26d7b9ed1b7c8d5ba659e824fd5b99fb19096313169432 +size 4996409992 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..ae5cc52 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f241156348251c9ed009dad06600725fe2adf85adceb5420bff385fbe9bfb5 +size 1413793632 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..f048659 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,6378 @@ +{ + "metadata": { + "total_size": 31392559104 + }, + "weight_map": { + "lm_head.weight": "model-00005-of-00007.safetensors", + "model.embed_tokens.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.30.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.59.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.32.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.32.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.34.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.59.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.59.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.57.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.20.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.49.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.54.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.63.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.21.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.18.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.38.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.24.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.24.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.19.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.31.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.25.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.25.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.26.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.56.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.27.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.53.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.28.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.29.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.29.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.56.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.8.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.30.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.18.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.31.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.62.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.53.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.norm.weight": "model-00001-of-00007.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..278b7f0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..b30d9b2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d44e2a3cfdfa7530be35f0d72c39b37ff438d4a1e69cc285b3ee461987d0bfa7 +size 17210623 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..fe5b44b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2092 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128256": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128257": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128258": { + "content": "<|NONE|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{# version=v3-llama3.1 #}{%- macro append_new_param_info(param_declaration, comment_info, examples_info, depth) -%}\n {%- set offset = \"\" -%}\n {%- if depth >= 1 -%}\n {%- set offset = \" \" * depth -%}\n {%- endif -%}\n {%- if comment_info != \"<|NONE|>\" -%}\n {{ \"\\n\" + offset + comment_info }}\n {%- if examples_info | length > 0 -%}\n {# Append each example info #}\n {%- for example in examples_info -%}\n {{ \"\\n\" + offset + \"// \" + example|string|replace(\"'\", '\"') }}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {{ \"\\n\" + offset + param_declaration }}\n{%- endmacro -%}\n\n{%- macro convert_data_type(param_type) -%}\n {%- if param_type == \"integer\" or param_type == \"float\" -%}\n {{ \"number\" }}\n {%- else -%}\n {{ param_type }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_param_type(param) -%}\n {%- set param_type = \"any\" -%}\n\n {%- if \"type\" in param -%}\n {%- set raw_param_type = param[\"type\"] -%}\n {%- if raw_param_type is iterable and raw_param_type is not string -%}\n {%- set param_type = raw_param_type | join(\" | \") -%}\n {%- else -%}\n {%- set param_type = raw_param_type -%}\n {%- endif -%}\n {{ convert_data_type(param_type) }}\n {%- elif \"oneOf\" in param -%}\n {%- set one_of_types = param[\"oneOf\"]|selectattr(\"type\", \"defined\")|list -%}\n {%- set one_of_types = one_of_types|map(attribute=\"type\")|unique|list -%}\n {{ convert_data_type(one_of_types | join(\" | \")) }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_format_param(param) -%}\n {%- if \"format\" in param -%}\n {{ param[\"format\"] }}\n {%- elif \"oneOf\" in param -%}\n {%- set formats = [] -%}\n {%- for item in param[\"oneOf\"] -%}\n {%- if \"format\" in item -%}\n {%- if item[\"format\"] == param[\"oneOf\"][-1][\"format\"] -%}\n {{ item[\"format\"] }}\n {%- else -%}\n {{ item[\"format\"] + \" or \"}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ \"<|NONE|>\" }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_param_info(param) -%}\n {%- set param_type = param.get(\"type\", \"any\") -%}\n {%- set format_param = get_format_param(param) -%}\n\n {%- if \"description\" in param or \"default\" in param or format_param != \"<|NONE|>\" or param[\"maximum\"] or param[\"minimum\"] or param[\"maxLength\"] or param[\"minLength\"] -%}\n {{ \"//\" }}\n {%- if \"description\" in param -%}\n {%- set desc = param[\"description\"] -%}\n {%- if not desc.endswith(\".\") -%}\n {%- set desc = desc + \".\" -%}\n {%- endif -%}\n {{ \" \" + desc }}\n {%- endif -%}\n\n {%- if \"default\" in param -%}\n {%- set default_value = param[\"default\"] -%}\n {%- if param_type == \"string\" -%}\n {%- set default_value = '\"' ~ default_value ~ '\"' -%}\n {%- endif -%}\n {{ \" Default=\" ~ default_value ~ \".\" }}\n {%- endif -%}\n\n {%- set format_param = get_format_param(param) -%}\n {%- if format_param != \"<|NONE|>\" -%}\n {{ \" Format=\" ~ format_param }}\n {%- endif -%}\n\n {%- for field, field_name in [(\"maximum\", \"Maximum\"), (\"minimum\", \"Minimum\"), (\"maxLength\", \"Maximum length\"), (\"minLength\", \"Minimum length\")] -%}\n {%- if field in param -%}\n {{ \" \" + field_name ~ \"=\" ~ param[field] }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ \"<|NONE|>\"}}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_enum_option_str(enum_options) -%}\n {%- for v in enum_options -%}\n {%- if v is string -%}\n {{ '\"' + v + '\"' }}\n {%- else -%}\n {{ v }}\n {%- endif -%}\n {%- if enum_options|length > 0 and v != enum_options[-1] -%}\n {{ \" | \" }}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n\n{%- macro get_array_typescript(param_name, param_dic, depth) -%}\n {%- set offset = '' -%}\n {%- if depth >= 1 -%}\n {%- set offset = \" \" * depth -%}\n {%- endif -%}\n {%- set items_info = param_dic.get('items', {}) -%}\n\n {%- if items_info|length == 0 -%}\n {%- if param_name -%}\n {{ \"\\n\" + offset + param_name + \": []\" }}\n {%- else -%}\n {{ \"\\n\" + offset + \"[]\" }}\n {%- endif -%}\n {%- else -%}\n {%- set array_type = get_param_type(items_info) -%}\n {%- if array_type == 'object' -%}\n {%- if param_name -%}\n {{ \"\\n\" + offset + param_name + \": {\" }}\n {%- else -%}\n {{ \"\\n\" + offset + \"{\" }}\n {%- endif -%}\n {{ get_parameter_typescript(items_info.get('properties', {}), items_info.get('required', []), depth + 1) -}}\n {{- \"\\n\" + offset + \"}[]\" }}\n {%- elif array_type == 'array' -%}\n {%- set item_info = get_array_typescript(None, items_info, depth + 1) -%}\n {%- if not param_name -%}\n {{ \"\\n\" + item_info + \"[]\" }}\n {%- else -%}\n {{ \"\\n\" + offset + param_name + \": \" + item_info|trim + \"[]\" }}\n {%- endif -%}\n {%- else -%}\n {%- if 'enum' in items_info -%}\n {%- set item_type = get_enum_option_str(items_info['enum']) -%}\n {%- if param_name is none -%}\n {{ \"(\" + item_type + \")[]\"}}\n {%- else -%}\n {{ \"\\n\" + offset + param_name + \": (\" + item_type + \")[]\" }}\n {%- endif -%}\n {%- else -%}\n {%- if param_name is none -%}\n {{ \"\\n\" + array_type + \"[]\" }}\n {%- else -%}\n {{ \"\\n\" + offset + param_name + \": \" + array_type + \"[],\" }}\n {%- endif -%}\n {%- endif -%}\n {%- endif -%}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_parameter_typescript(properties, required_params, depth=0) -%}\n {%- set res = \"\" -%}\n {%- for param_name, param in properties.items() -%}\n {%- if param is mapping -%}\n {%- set comment_info = get_param_info(param) -%}\n {# Param Examples #}\n {%- set examples_info = [] -%}\n {%- if \"examples\" in param -%}\n {%- set examples_info = [\"Example \" + param_name + \":\"] -%}\n {%- set examples_info = examples_info + param[\"examples\"] -%}\n {%- endif -%}\n\n {# Param Name declaration #}\n {%- set param_declaration = param_name -%}\n {%- if required_params is iterable and param_name not in required_params -%}\n {%- set param_declaration = param_declaration + \"?\" -%}\n {%- endif -%}\n\n {%- set param_type = get_param_type(param) -%}\n\n {# Handle indentation based on depth #}\n {%- set offset = \"\" -%}\n {%- if depth >= 1 -%}\n {%- set offset = \" \" * depth -%}\n {%- endif -%}\n\n {%- if param_type == \"object\" -%}\n {%- if comment_info != \"<|NONE|>\" -%}\n {{ \"\\n\" + offset + comment_info }}\n {%- endif -%}\n {%- if examples_info|length > 0 -%}\n {%- for example in examples_info -%}\n {{ \"\\n\" + offset + \"// \" + example|string|replace(\"'\", '\"') }}\n {%- endfor -%}\n {%- endif -%}\n {%- set param_declaration = param_declaration + \": {\" -%}\n {{ \"\\n\" + offset + param_declaration -}}\n {{- get_parameter_typescript(param.get(\"properties\", {}), param.get(\"required\", []), depth + 1) -}}\n {{- \"\\n\" + offset + \"},\" }}\n {%- elif param_type == \"array\" -%}\n {%- set item_info = param.get(\"items\", {}) -%}\n {%- if \"type\" not in item_info -%}\n {%- set param_declaration = param_declaration + \": [],\" -%}\n {{ append_new_param_info(param_declaration, comment_info, examples_info, depth) }}\n {%- else -%}\n {%- if comment_info != \"<|NONE|>\" -%}\n {{ \"\\n\" + offset + comment_info }}\n {%- endif -%}\n {%- if examples_info|length > 0 -%}\n {%- for example in examples_info -%}\n {{ \"\\n\" + offset + \"// \" + example|string|replace(\"'\", '\"') }}\n {%- endfor -%}\n {%- endif -%}\n {%- set array_declaration = get_array_typescript(param_declaration, param, depth) -%}\n {%- if not array_declaration.endswith(\",\") -%}\n {%- set array_declaration = array_declaration + \",\" -%}\n {%- endif -%}\n {{ array_declaration}}\n {%- endif -%}\n {%- else -%}\n {%- if \"enum\" in param -%}\n {%- set param_type = get_enum_option_str(param[\"enum\"]) -%}\n {%- endif -%}\n {%- if \"nullable\" in param and param[\"nullable\"] -%}\n {%- set param_type = param_type + \" | null\" -%}\n {%- endif -%}\n {%- set param_declaration = param_declaration + \": \" + param_type + \",\" -%}\n {{ append_new_param_info(param_declaration, comment_info, examples_info, depth) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n\n{%- macro generate_schema_from_functions(functions, namespace='functions') -%}\n {{ \"// Supported function definitions that should be called when necessary.\\n\" -}}\n {{- \"namespace \" + namespace + \" {\\n\\n\" -}}\n\n {%- for function in functions -%}\n {%- if function.get(\"function\") -%}\n {%- set function = function.get(\"function\") -%}\n {%- endif -%}\n\n {%- set function_name = function.get(\"name\") -%}\n {%- if function_name -%}\n {%- set description = function.get('description', '') -%}\n {%- set parameters = function.get('parameters', {}) -%}\n {{- \"// \" + description + \"\\n\" -}}\n {{- \"type \" + function_name -}}\n {%- if parameters and parameters.get(\"properties\") -%}\n {{- \" = (_: {\" -}}\n {%- set required_params = parameters.get(\"required\", []) -%}\n {{ get_parameter_typescript(parameters.get(\"properties\"), required_params, 0) -}}\n {{- \"\\n}) => any;\\n\\n\" }}\n {%- else -%}\n {{ \" = () => any;\\n\\n\" }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {{ \"} // namespace \" + namespace }}\n{%- endmacro -%}\n\n{%- if not tools is defined -%}\n {%- set tools = none -%}\n{%- endif -%}\n\n{%- set has_code_interpreter = tools | selectattr(\"type\", \"equalto\", \"code_interpreter\") | list | length > 0 -%}\n{%- if has_code_interpreter -%}\n {%- set tools = tools | rejectattr(\"type\", \"equalto\", \"code_interpreter\") | list -%}\n{%- endif -%}\n\n{#- System message + builtin tools #}\n{{- bos_token + \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if has_code_interpreter %}\n {{- \"Environment: ipython\\n\\n\" }}\n{%- else -%}\n {{ \"\"}}\n{%- endif %}\n{%- if tools %}\n {{- \"\\nYou have access to the following functions:\\n\\n\" }}\n {%- for t in tools %}\n {%- if \"type\" in t -%}\n {{ \"Use the function '\" + t[\"function\"][\"name\"] + \"' to '\" + t[\"function\"][\"description\"] + \"'\\n\" + t[\"function\"] | tojson() }}\n {%- else -%}\n {{ \"Use the function '\" + t[\"name\"] + \"' to '\" + t[\"description\"] + \"'\\n\" + t | tojson }}\n {%- endif -%}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- '\\nThink very carefully before calling functions.\\nIf a you choose to call a function ONLY reply in the following format:\\n<{start_tag}={function_name}>{parameters}{end_tag}\\nwhere\\n\\nstart_tag => ` a JSON dict with the function argument name as key and function argument value as value.\\nend_tag => ``\\n\\nHere is an example,\\n{\"example_name\": \"example_value\"}\\n\\nReminder:\\n- If looking for real time information use relevant functions before falling back to brave_search\\n- Function calls MUST follow the specified format, start with \\n- Required parameters MUST be specified\\n- Only call one function at a time\\n- Put the entire function call reply on one line\\n\\n' -}}\n{%- endif %}\n{{- \"<|eot_id|>\" -}}\n\n{%- for message in messages -%}\n {%- if message['role'] == 'user' or message['role'] == 'system' -%}\n {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' + message['content'] + '<|eot_id|>' }}\n {%- elif message['role'] == 'tool' -%}\n {{ '<|start_header_id|>ipython<|end_header_id|>\\n\\n' + message['content'] + '<|eot_id|>' }}\n {%- else -%}\n {%- if (message['content'] and message['content']|length > 0) or ('tool_calls' in message and message['tool_calls'] and message['tool_calls']|length > 0) -%}\n {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'}}\n {%- endif -%}\n {%- if message['content'] and message['content']|length > 0 -%}\n {{ message['content'] }}\n {%- endif -%}\n {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls']|length > 0 -%}\n {%- for tool_call in message['tool_calls'] -%}\n {%- if tool_call[\"function\"][\"name\"] == \"python\" -%}\n {{ '<|python_tag|>' + tool_call['function']['arguments'] }}\n {%- else -%}\n {{ '' + tool_call['function']['arguments'] + '' }}\n {%- endif -%}\n {%- endfor -%}\n {{ '<|eom_id|>' }}\n {%- elif message['content'] and message['content']|length > 0 -%}\n {{ '<|eot_id|>' }}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{ '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif -%}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "max_length": 8192, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|end_of_text|>", + "stride": 0, + "tokenizer_class": "PreTrainedTokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first" +}