初始化项目，由ModelHub XC社区提供模型
Model: cyankiwi/Nemotron-Orchestrator-8B-AWQ-4bit Source: Original Platform
This commit is contained in:
ModelHub XC
53
.gitattributes
vendored
Normal file
53
.gitattributes
vendored
Normal file
@@ -0,0 +1,53 @@
|
||||
*.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
|
||||
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
35
LICENSE
Normal file
35
LICENSE
Normal file
@@ -0,0 +1,35 @@
|
||||
NVIDIA License
|
||||
|
||||
1. Definitions
|
||||
|
||||
“Licensor” means any person or entity that distributes its Work.
|
||||
“Work” means (a) the original work of authorship made available under this license, which may include software, documentation, or other files, and (b) any additions to or derivative works thereof that are made available under this license.
|
||||
The terms “reproduce,” “reproduction,” “derivative works,” and “distribution” have the meaning as provided under U.S. copyright law; provided, however, that for the purposes of this license, derivative works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work.
|
||||
Works are “made available” under this license by including in or with the Work either (a) a copyright notice referencing the applicability of this license to the Work, or (b) a copy of this license.
|
||||
|
||||
2. License Grant
|
||||
|
||||
2.1 Copyright Grant. Subject to the terms and conditions of this license, each Licensor grants to you a perpetual, worldwide, non-exclusive, royalty-free, copyright license to use, reproduce, prepare derivative works of, publicly display, publicly perform, sublicense and distribute its Work and any resulting derivative works in any form.
|
||||
|
||||
3. Limitations
|
||||
|
||||
3.1 Redistribution. You may reproduce or distribute the Work only if (a) you do so under this license, (b) you include a complete copy of this license with your distribution, and (c) you retain without modification any copyright, patent, trademark, or attribution notices that are present in the Work.
|
||||
|
||||
3.2 Derivative Works. You may specify that additional or different terms apply to the use, reproduction, and distribution of your derivative works of the Work (“Your Terms”) only if (a) Your Terms provide that the use limitation in Section 3.3 applies to your derivative works, and (b) you identify the specific derivative works that are subject to Your Terms. Notwithstanding Your Terms, this license (including the redistribution requirements in Section 3.1) will continue to apply to the Work itself.
|
||||
|
||||
3.3 Use Limitation. The Work and any derivative works thereof only may be used or intended for use non-commercially. Notwithstanding the foregoing, NVIDIA Corporation and its affiliates may use the Work and any derivative works commercially. As used herein, “non-commercially” means for non-commercial research activities or non-commercial research publications only.
|
||||
|
||||
3.4 Patent Claims. If you bring or threaten to bring a patent claim against any Licensor (including any claim, cross-claim or counterclaim in a lawsuit) to enforce any patents that you allege are infringed by any Work, then your rights under this license from such Licensor (including the grant in Section 2.1) will terminate immediately.
|
||||
|
||||
3.5 Trademarks. This license does not grant any rights to use any Licensor’s or its affiliates’ names, logos, or trademarks, except as necessary to reproduce the notices described in this license.
|
||||
|
||||
3.6 Termination. If you violate any term of this license, then your rights under this license (including the grant in Section 2.1) will terminate immediately.
|
||||
|
||||
4. Disclaimer of Warranty.
|
||||
|
||||
THE WORK IS PROVIDED “AS IS” WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR NON-INFRINGEMENT. YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER THIS LICENSE.
|
||||
|
||||
5. Limitation of Liability.
|
||||
|
||||
EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK (INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION, LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
|
||||
95
README.md
Normal file
95
README.md
Normal file
@@ -0,0 +1,95 @@
|
||||
---
|
||||
library_name: transformers
|
||||
base_model:
|
||||
- nvidia/Nemotron-Orchestrator-8B
|
||||
---
|
||||
# ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
|
||||
|
||||
[](https://arxiv.org/abs/2511.21689)
|
||||
[](https://github.com/NVlabs/ToolOrchestra/)
|
||||
[](https://huggingface.co/nvidia/Orchestrator-8B)
|
||||
[](https://huggingface.co/datasets/nvidia/ToolScale)
|
||||
[](https://research.nvidia.com/labs/lpr/ToolOrchestra/)
|
||||
|
||||
|
||||
### Description
|
||||
|
||||
Orchestrator-8B is a state-of-the-art 8B parameter orchestration model designed to solve complex, multi-turn agentic tasks by coordinating a diverse set of expert models and tools.
|
||||
<p align="center">
|
||||
<img src="https://raw.githubusercontent.com/NVlabs/ToolOrchestra/main/assets/method.png" width="100%"/>
|
||||
<p>
|
||||
|
||||
|
||||
On the Humanity's Last Exam (HLE) benchmark, ToolOrchestrator-8B achieves a score of 37.1%, outperforming GPT-5 (35.1%) while being approximately 2.5x more efficient.
|
||||
|
||||
<p align="center">
|
||||
<img src="https://raw.githubusercontent.com/NVlabs/ToolOrchestra/main/assets/HLE_benchmark.png" width="80%"/>
|
||||
<p>
|
||||
|
||||
This model is for research and development only.
|
||||
|
||||
|
||||
### Key Features
|
||||
|
||||
- Intelligent Orchestration: Capable of managing heterogeneous toolsets including basic tools (search, code execution) and other LLMs (specialized and generalist).
|
||||
- Multi-Objective RL Training: Trained via Group Relative Policy Optimization (GRPO) with a novel reward function that optimizes for accuracy, latency/cost, and adherence to user preferences.
|
||||
- Efficiency: Delivers higher accuracy at significantly lower computational cost compared to monolithic frontier models.
|
||||
- Robust Generalization: Demonstrated ability to generalize to unseen tools and pricing configurations.
|
||||
|
||||
### Benchmark
|
||||
On Humanity’s Last Exam, Orchestrator-8B achieves 37.1%, surpassing GPT-5 (35.1%) with only 30% monetary cost and 2.5x faster. On FRAMES and τ²-Bench, Orchestrator-8B consistently outperforms strong monolithic systems, demonstrating versatile reasoning and robust tool orchestration.
|
||||
|
||||
<p align="center">
|
||||
<img src="https://raw.githubusercontent.com/NVlabs/ToolOrchestra/main/assets/results.png" width="100%"/>
|
||||
<p>
|
||||
|
||||
Orchestrator-8B consistently outperforms GPT-5, Claude Opus 4.1 and Qwen3-235B-A22B on HLE with substantially lower cost.
|
||||
<p align="center">
|
||||
<img src="https://raw.githubusercontent.com/NVlabs/ToolOrchestra/main/assets/cost_performance.png" width="60%"/>
|
||||
<p>
|
||||
|
||||
|
||||
### Model Details
|
||||
|
||||
- Developed by: NVIDIA & University of Hong Kong
|
||||
- Model Type: Decoder-only Transformer
|
||||
- Base Model: [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
|
||||
- Parameters: 8B
|
||||
- Language(s): English
|
||||
- License: NVIDIA License
|
||||
|
||||
### Model Version(s):
|
||||
1.0 <br>
|
||||
|
||||
### Training Dataset:
|
||||
**Link:**
|
||||
| Dataset | Link |
|
||||
|---------------------------|-------------------------------------------------------------------------------------------|
|
||||
| GeneralThought-430K | [Link](https://huggingface.co/datasets/natolambert/GeneralThought-430K-filtered) |
|
||||
| ToolScale | [Link](https://huggingface.co/datasets/nvidia/ToolScale) |
|
||||
|
||||
|
||||
|
||||
### 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 internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. <br>
|
||||
|
||||
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://app.intigriti.com/programs/nvidia/nvidiavdp/detail).
|
||||
|
||||
|
||||
### License/Terms of Use
|
||||
[NVIDIA License](LICENSE)
|
||||
|
||||
|
||||
### Citation
|
||||
If you find this model useful, please cite our [paper](https://arxiv.org/abs/2511.21689):
|
||||
```
|
||||
@misc{toolorchestra,
|
||||
title={ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration},
|
||||
author={Hongjin Su and Shizhe Diao and Ximing Lu and Mingjie Liu and Jiacheng Xu and Xin Dong and Yonggan Fu and Peter Belcak and Hanrong Ye and Hongxu Yin and Yi Dong and Evelina Bakhturina and Tao Yu and Yejin Choi and Jan Kautz and Pavlo Molchanov},
|
||||
year={2025},
|
||||
eprint={2511.21689},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2511.21689},
|
||||
}
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 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
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
103
config.json
Normal file
103
config.json
Normal file
@@ -0,0 +1,103 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"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": 4,
|
||||
"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.a20251110"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.0.0.dev0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2de3a5ac3402bd1b9525f9b47e37e3b531f5e055a114c571f160b1faa12e891c
|
||||
size 4987181352
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:90e2f9de719a64c9af4286299fe302204e2d7545fbdee3445b4012eb2f74f94d
|
||||
size 1409855888
|
||||
911
model.safetensors.index.json
Normal file
911
model.safetensors.index.json
Normal file
@@ -0,0 +1,911 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 2330244600,
|
||||
"total_size": 6396934080
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight_packed": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight_shape": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
36
recipe.yaml
Normal file
36
recipe.yaml
Normal file
@@ -0,0 +1,36 @@
|
||||
default_stage:
|
||||
default_modifiers:
|
||||
AWQModifier:
|
||||
config_groups:
|
||||
group_0:
|
||||
targets: [Linear]
|
||||
weights:
|
||||
num_bits: 4
|
||||
type: int
|
||||
symmetric: true
|
||||
group_size: 32
|
||||
strategy: group
|
||||
block_structure: null
|
||||
dynamic: false
|
||||
actorder: null
|
||||
scale_dtype: null
|
||||
zp_dtype: null
|
||||
observer: mse
|
||||
observer_kwargs: {}
|
||||
input_activations: null
|
||||
output_activations: null
|
||||
format: null
|
||||
targets: [Linear]
|
||||
ignore: [model.embed_tokens, 're:.*input_layernorm$', 're:.*post_attention_layernorm$',
|
||||
model.norm, lm_head]
|
||||
mappings:
|
||||
- smooth_layer: re:.*input_layernorm$
|
||||
balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
|
||||
- smooth_layer: re:.*v_proj$
|
||||
balance_layers: ['re:.*o_proj$']
|
||||
- smooth_layer: re:.*post_attention_layernorm$
|
||||
balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
|
||||
- smooth_layer: re:.*up_proj$
|
||||
balance_layers: ['re:.*down_proj$']
|
||||
duo_scaling: true
|
||||
n_grid: 20
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -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": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"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": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"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 <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|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('<tool_response>') and message.content.endswith('</tool_response>')) %}\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 '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-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<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\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 {{- '<tool_call>\\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</tool_call>' }}\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<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\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 {{- '<think>\\n\\n</think>\\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
|
||||
}
|
||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user