From fbcda19f57a47821f90d58d6d2f8ddb5451d0e28 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 15 Oct 2026 20:30:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: cyankiwi/Qwen3-Nemotron-32B-RLBFF-AWQ-8bit Source: Original Platform --- .gitattributes | 59 ++ README.md | 266 +++++ added_tokens.json | 28 + config.json | 131 +++ configuration.json | 1 + generation_config.json | 9 + merges.txt | 3 + model-00001-of-00008.safetensors | 3 + model-00002-of-00008.safetensors | 3 + model-00003-of-00008.safetensors | 3 + model-00004-of-00008.safetensors | 3 + model-00005-of-00008.safetensors | 3 + model-00006-of-00008.safetensors | 3 + model-00007-of-00008.safetensors | 3 + model-00008-of-00008.safetensors | 3 + model.safetensors.index.json | 1611 ++++++++++++++++++++++++++++++ special_tokens_map.json | 31 + tokenizer.json | 3 + tokenizer_config.json | 240 +++++ vocab.json | 3 + 20 files changed, 2409 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model-00001-of-00008.safetensors create mode 100644 model-00002-of-00008.safetensors create mode 100644 model-00003-of-00008.safetensors create mode 100644 model-00004-of-00008.safetensors create mode 100644 model-00005-of-00008.safetensors create mode 100644 model-00006-of-00008.safetensors create mode 100644 model-00007-of-00008.safetensors create mode 100644 model-00008-of-00008.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb3469a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 + +*.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 + +model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..005b90a --- /dev/null +++ b/README.md @@ -0,0 +1,266 @@ +--- +license: other +license_name: nvidia-open-model-license +license_link: >- + https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ +inference: false +fine-tuning: false +language: +- en +tags: + - nvidia + - qwen3 +datasets: + - nvidia/HelpSteer3 +base_model: nvidia/Qwen3-Nemotron-32B-RLBFF +library_name: transformers +--- + +# Qwen3-Nemotron-32B-RLBFF AWQ - INT8 + +## Model Details + +- **Quantization Method:** AWQ +- **Bits:** 8 +- **Group Size:** 32 +- **Calibration Dataset:** [nvidia/Llama-Nemotron-Post-Training-Dataset](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset) +- **Quantization Tool:** [llm-compressor](https://github.com/vllm-project/llm-compressor) + +## Inference + +### Prerequisite + +```bash +pip install -U vllm +``` + +### Basic Usage + +```bash +vllm serve cyankiwi/Qwen3-Nemotron-32B-RLBFF-AWQ-8bit +``` +## Additional Information + +### Changelog + +- **v1.0.0** - Initial quantized release + +### Authors + +- **Name:** cyankiwi + +- **Contacts:** ton@cyan.kiwi + +# Model Overview + +## Description: + +Qwen3-Nemotron-32B-RLBFF is a large language model that leverages Qwen/Qwen3-32B as the foundation and is fine-tuned to improve the quality of LLM-generated responses in the default thinking mode. + +Given a conversation with multiple turns between user and assistant and a user-specified principle, it generates a response the final user turn. + +**This is a research model** described in and is released to support the following research paper: [https://arxiv.org/abs/2509.21319](https://arxiv.org/abs/2509.21319) + +As of 24 Sep 2025, this model achieves [Arena Hard V2](https://github.com/lmarena/arena-hard-auto) of 55.6% and [WildBench](https://huggingface.co/spaces/allenai/WildBench) Score of 70.33% and [MT Bench](https://arxiv.org/abs/2306.05685) of 9.50. This means that our model is substantially improved over the initial Qwen3-32B model and has similar performance compared to DeepSeek R1 and O3-mini at less than 5% of the inference cost (as indicated on openrouter). + + +## License/Terms of Use: + +GOVERNING TERMS: Use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). + + +### Deployment Geography + +Global + +## Use Case: + +Qwen3-Nemotron-32B-RLBFF generates an response to a user query. + +## Release Date: + +HuggingFace 10/27/2025 via https://huggingface.co/nvidia/Qwen3-Nemotron-32B-RLBFF + +## References: + +* [RLBFF](https://arxiv.org/abs/2509.21319) +* [HelpSteer3](https://arxiv.org/abs/2503.04378) +* [HelpSteer3-Preference](https://arxiv.org/abs/2505.11475) +* [HelpSteer2-Preference](https://arxiv.org/abs/2410.01257) +* [SteerLM method](https://arxiv.org/abs/2310.05344) +* [HelpSteer](https://arxiv.org/abs/2311.09528) +* [HelpSteer2](https://arxiv.org/abs/2406.08673) + + +## LeaderBoards + +Arena Hard V2, WildBench and MT Bench are common benchmarks for measuring general-domain model capabilities. + +| Model | MT Bench (GPT-4-Turbo) | Arena Hard v2 (95% CI) | WildBench Overall | Creative | Planning | Data Analy. | Info. Seek. | Coding | In/M | Out/M | Cost | +|:--------------------------------------------|:------------------:|:----------------------:|:----------------:|:---------:|:---------:|:-----------:|:-----------:|:-------:|:----:|:----:|:----:| +| **Qwen3-Nemotron-32B-RLBFF** | **9.50** | _55.6_ (-1.6 / +1.4) | _70.33_ | 71.73 | 70.73 | 69.37 | 68.96 | 70.94 | 0.018 | 0.072 | **1×** | +| Qwen3-32B | 9.38 | 44.0 (-1.6 / +1.5) | 67.57 | 68.63 | 67.95 | 64.68 | 66.78 | 69.53 | 0.018 | 0.072 | **1×** | +| o3-mini | 9.26 | 50.0 (-0.0 / +0.0) | **71.64** | 69.04 | 72.44 | 74.37 | 65.81 | 73.21 | 1.1 | 4.4 | 61× | +| Claude-3.7-Sonnet (Thinking) | 8.93 | 54.2 (-2.0 / +1.8) | 65.45 | 66.72 | 65.94 | 63.59 | 63.08 | 67.36 | 3 | 15 | 188× | +| DeepSeek R1 | _9.49_ | **57.4** (-2.0 / +2.0) | 64.24 | 70.75 | 66.29 | 59.20 | 68.56 | 61.04 | 0.4 | 2 | _25×_ | + + +## Model Architecture: +**Architecture Type:** Transformer
+**Network Architecture:** Qwen3
+ +We developed this model using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as its foundation. This model contains 32 billion parameters. + +## Input: +**Input Type(s):** Text
+**Input Format:** String
+**Input Parameters:** One Dimensional (1D)
+**Other Properties Related to Input:** Max of 128k tokens (but trained only on conversations up to 4K tokens)
+ +## Output: +**Output Type(s):** Text
+**Output Format:** String
+**Output Parameters:** One-Dimensional (1D)
+**Other Properties Related to Output:**
+ +Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
+ +## Software Integration: +**Runtime Engine(s):**
+* [NeMo-RL - 0.3]
+ +**Supported Hardware Microarchitecture Compatibility:**
+* NVIDIA Ampere
+* NVIDIA Hopper
+* NVIDIA Turing
+ +**Supported Operating System(s):** Linux
+ +## Quick Start + +You can use the model using HuggingFace Transformers library with 1 or more 80GB GPUs (NVIDIA Ampere or newer) with at least 70GB of free disk space to accomodate the download. Alternatively, you can use vLLM for accelerated inference. + +This code has been tested on Transformers v4.57.0, torch v2.3.0a0+40ec155e58.nv24.3 and 1 H100 80GB GPUs, but any setup that supports Qwen/Qwen3-32B should support this model as well. If you run into problems, you can consider doing pip install -U transformers. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF" + +model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto") +tokenizer = AutoTokenizer.from_pretrained(model_name) + +prompt = "How many r are there in strawberry?" + +messages = [{'role': "user", "content": prompt}] + +tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True) + +response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(), max_new_tokens=16000, return_dict_in_generate=True, output_scores=True) + +response = tokenizer.decode(response_token_ids.sequences[0].tolist()) + +print(response) +``` + +## Model Version: +v1.0 + +# Training, Testing and Evaluation Datasets: + +## Training Datasets: + +**Dataset Name:** HelpSteer3
+**Dataset Link:** https://huggingface.co/datasets/nvidia/HelpSteer3 + +**Data Collection Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Labeling Method by dataset**
+* [Human]
+ +**Properties:**
+* 77,564 prompt-responses, each annotated with up to 3 annotations of free-text feedback (each being 50-250 words long) elaborating upon the overall helpfulness of the response. + +## Testing Datasets: + +**Dataset Name:** HelpSteer3
+**Dataset Link:** https://huggingface.co/datasets/nvidia/HelpSteer3 + +**Data Collection Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Labeling Method by dataset**
+* [Human]
+ +**Properties:**
+* 4,078 prompt-responses, each annotated with up to 3 annotations of free-text feedback (each being 50-250 words long) elaborating upon the overall helpfulness of the response. + +## Evaluation Datasets + +**Dataset Name:** Arena Hard Auto V2
+**Dataset Link:** https://github.com/lmarena/arena-hard-auto + +**Data Collection Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Labeling Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Properties:**
+* 500 prompts + + +**Dataset Name:** WildBench
+**Dataset Link:** https://github.com/allenai/WildBench + +**Data Collection Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Labeling Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Properties:**
+* 1024 prompts + + +**Dataset Name:** MT-Bench
+**Dataset Link:** https://huggingface.co/spaces/lmsys/mt-bench + +**Data Collection Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Labeling Method by dataset**
+* [Hybrid: Human, Synthetic]
+ +**Properties:**
+* 160 prompts + + +# Inference: +**Engine:** PyTorch
+**Test Hardware:** H100, A100 80GB, A100 40GB
+ + +## Ethical Considerations: +NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. +For more detailed information on ethical considerations for this model, please see the Model Card++ [Explainability](explainability.md), [Bias](bias.md), [Safety and Security](safety.md), and [Privacy](privacy.md) Subcards. + +Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). + +## Citation + +If you find this model useful, please cite the following work: + +```bibtex +@misc{wang2025rlbffbinaryflexiblefeedback, + title={RLBFF: Binary Flexible Feedback to bridge between Human Feedback | Verifiable Rewards}, + author={Zhilin Wang and Jiaqi Zeng and Olivier Delalleau and Ellie Evans and Daniel Egert and Hoo-Chang Shin and Felipe Soares and Yi Dong and Oleksii Kuchaiev}, + year={2025}, + eprint={2509.21319}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2509.21319}, +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..583f973 --- /dev/null +++ b/config.json @@ -0,0 +1,131 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 25600, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 64, + "model_type": "qwen3", + "num_attention_heads": 64, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "quantization_config": { + "config_groups": { + "group_0": { + "format": "pack-quantized", + "input_activations": null, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": 32, + "num_bits": 8, + "observer": "mse", + "observer_kwargs": {}, + "strategy": "group", + "symmetric": true, + "type": "int" + } + } + }, + "format": "pack-quantized", + "global_compression_ratio": null, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": {}, + "transform_config": {}, + "version": "0.12.3.dev20+gd429903" + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file 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..97025b7 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": 151645, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.57.0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00008.safetensors b/model-00001-of-00008.safetensors new file mode 100644 index 0000000..2b78fe0 --- /dev/null +++ b/model-00001-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5e6e5a63d5c650414aa73930b7906be317aa9f399b6492ba620f6b0865e427 +size 4903877600 diff --git a/model-00002-of-00008.safetensors b/model-00002-of-00008.safetensors new file mode 100644 index 0000000..3e8aba9 --- /dev/null +++ b/model-00002-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dea69579f453e94d90c26ad80f1d89f53a8e1ebabe8de067e5675121928392e +size 4997030472 diff --git a/model-00003-of-00008.safetensors b/model-00003-of-00008.safetensors new file mode 100644 index 0000000..760f9cf --- /dev/null +++ b/model-00003-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7367ec40c837f502a15616ebb7529a9fe2b1273987525a57236ce44029f41415 +size 4985868728 diff --git a/model-00004-of-00008.safetensors b/model-00004-of-00008.safetensors new file mode 100644 index 0000000..149b7c6 --- /dev/null +++ b/model-00004-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fb1ed634daacace70d55f6446c1c697061d2afce5b26b45daaca8644c15e09 +size 4902331784 diff --git a/model-00005-of-00008.safetensors b/model-00005-of-00008.safetensors new file mode 100644 index 0000000..95e7ffc --- /dev/null +++ b/model-00005-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2b035fe0c12df52ae96b9b39a5f4cc5abd736d34866f0c7a4d3e6f76f45cdf +size 4941303152 diff --git a/model-00006-of-00008.safetensors b/model-00006-of-00008.safetensors new file mode 100644 index 0000000..ae7aab4 --- /dev/null +++ b/model-00006-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccf4751b9ab246d28046288889dcb291c20a223fbf016fde28eb15c6bf5aaa2 +size 4902331784 diff --git a/model-00007-of-00008.safetensors b/model-00007-of-00008.safetensors new file mode 100644 index 0000000..69f6cf7 --- /dev/null +++ b/model-00007-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e87f0f3b9a02ed0df4cef6cc1bd404d4776c2a5f5bf036e2b63a2e4f721f74 +size 4941303152 diff --git a/model-00008-of-00008.safetensors b/model-00008-of-00008.safetensors new file mode 100644 index 0000000..1efb2c5 --- /dev/null +++ b/model-00008-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d722aa3c9c6c011585b5647308af2aa7ec358ebec8945824f636e3e73ac6f89 +size 1695120056 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d65af4c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1611 @@ +{ + "metadata": { + "total_parameters": 10333083520, + "total_size": 36268983296 + }, + "weight_map": { + "lm_head.weight": "model-00008-of-00008.safetensors", + "model.embed_tokens.weight": "model-00001-of-00008.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.10.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.11.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.12.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.13.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.14.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.15.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.16.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.16.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.16.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.16.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.16.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.17.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.18.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.19.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.20.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.21.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.22.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.23.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.down_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.24.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.25.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.25.mlp.down_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.mlp.gate_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.25.mlp.gate_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.mlp.up_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.25.mlp.up_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.k_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.k_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.o_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.o_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.q_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.q_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.v_proj.weight_packed": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00003-of-00008.safetensors", + "model.layers.25.self_attn.v_proj.weight_shape": "model-00003-of-00008.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.26.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.27.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.28.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.29.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.30.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.31.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.32.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.33.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.down_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.down_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.down_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.gate_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.gate_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.up_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.up_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.mlp.up_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.34.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.gate_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.35.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.35.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.k_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.k_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.k_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.o_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.o_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.o_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.q_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.q_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.q_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.v_proj.weight_packed": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.v_proj.weight_scale": "model-00004-of-00008.safetensors", + "model.layers.35.self_attn.v_proj.weight_shape": "model-00004-of-00008.safetensors", + "model.layers.36.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.36.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.37.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.38.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.39.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.40.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.40.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.41.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.42.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.down_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.down_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.43.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.44.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.44.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.44.mlp.down_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.mlp.gate_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.44.mlp.gate_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.44.mlp.gate_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.mlp.up_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.44.mlp.up_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.44.mlp.up_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.k_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.k_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.k_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.o_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.o_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.o_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.q_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.q_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.q_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.v_proj.weight_packed": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.v_proj.weight_scale": "model-00005-of-00008.safetensors", + "model.layers.44.self_attn.v_proj.weight_shape": "model-00005-of-00008.safetensors", + "model.layers.45.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.45.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.46.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.47.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.48.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.49.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.50.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.51.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.52.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.down_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.down_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.down_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.gate_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.gate_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.up_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.up_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.mlp.up_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.53.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.54.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.gate_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.54.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.54.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.k_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.k_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.k_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.o_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.o_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.o_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.q_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.q_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.q_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.v_proj.weight_packed": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.v_proj.weight_scale": "model-00006-of-00008.safetensors", + "model.layers.54.self_attn.v_proj.weight_shape": "model-00006-of-00008.safetensors", + "model.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.55.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.56.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.57.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.58.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.59.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.6.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00008.safetensors", + "model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00008.safetensors", + "model.layers.60.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.60.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.61.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.down_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.down_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.62.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.input_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.63.mlp.down_proj.weight_packed": "model-00008-of-00008.safetensors", + "model.layers.63.mlp.down_proj.weight_scale": "model-00008-of-00008.safetensors", + "model.layers.63.mlp.down_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.mlp.gate_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.63.mlp.gate_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.63.mlp.gate_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.mlp.up_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.63.mlp.up_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.63.mlp.up_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.k_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.k_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.k_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.o_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.o_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.o_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.q_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.q_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.q_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.v_proj.weight_packed": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.v_proj.weight_scale": "model-00007-of-00008.safetensors", + "model.layers.63.self_attn.v_proj.weight_shape": "model-00007-of-00008.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.8.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.down_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.down_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.gate_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.gate_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.up_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.mlp.up_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.k_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.k_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.o_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.o_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.q_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.q_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.v_proj.weight_packed": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00002-of-00008.safetensors", + "model.layers.9.self_attn.v_proj.weight_shape": "model-00002-of-00008.safetensors", + "model.norm.weight": "model-00008-of-00008.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3fb4394 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833