From ca46bf799f6b63a43b08c4091817a349fd8b0854 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 23 Oct 2026 05:31:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: dwetzel/DeepSeek-R1-Distill-Qwen-32B-GPTQ-INT4 Source: Original Platform --- .gitattributes | 36 + README.md | 323 ++++++ config.json | 519 +++++++++ generation_config.json | 9 + model-00001-of-00005.safetensors | 3 + model-00002-of-00005.safetensors | 3 + model-00003-of-00005.safetensors | 3 + model-00004-of-00005.safetensors | 3 + model-00005-of-00005.safetensors | 3 + model.safetensors.index.json | 1674 ++++++++++++++++++++++++++++++ recipe.yaml | 7 + special_tokens_map.json | 23 + tokenizer.json | 3 + tokenizer_config.json | 194 ++++ 14 files changed, 2803 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00005.safetensors create mode 100644 model-00002-of-00005.safetensors create mode 100644 model-00003-of-00005.safetensors create mode 100644 model-00004-of-00005.safetensors create mode 100644 model-00005-of-00005.safetensors create mode 100644 model.safetensors.index.json create mode 100644 recipe.yaml create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c9eb3c --- /dev/null +++ b/README.md @@ -0,0 +1,323 @@ +--- +license: mit +library_name: transformers +--- +# DeepSeek-R1 + + + + +
+ DeepSeek-V3 +
+
+
+ + Homepage + + + Chat + + + Hugging Face + +
+ +
+ + Discord + + + Wechat + + + Twitter Follow + +
+ +
+ + License + +
+ + +

+ Paper Link👁️ +

+ + + +# QUANTIZATION INFORMATION + +This model was quantized using the [llm-compressor](https://github.com/vllm-project/llm-compressor) library from the vLLM team. + +The calibration dataset was [ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) with a sequence length of `4096` and a sample size of `1024` + +The quantiation scheme is `W4A16` with the `lm_head` ignored. + +Further Parameters were the llm-compressor defaults. + + +## QUANTIZATION CODE + +The following code was used to quantize this model: + +#### LOADING THE MODEL: + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +MODEL_ID = "mistralai/Mistral-Small-24B-Instruct-2501" + +# Load model with better memory management +model = AutoModelForCausalLM.from_pretrained( + MODEL_ID, + device_map="auto", + torch_dtype=torch.bfloat16, +) +tokenizer = AutoTokenizer.from_pretrained(MODEL_ID) +``` + +#### LOADING THE DATASET: +```python +from datasets import load_dataset + +NUM_CALIBRATION_SAMPLES=1024 +MAX_SEQUENCE_LENGTH=4096 + +# Load dataset. +ds = load_dataset("HuggingFaceH4/ultrachat_200k", split="train_sft") +ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES)) + +# Preprocess the data into the format the model is trained with. +def preprocess(example): + return {"text": tokenizer.apply_chat_template(example["messages"], tokenize=False,)} +ds = ds.map(preprocess) + +# Tokenize the data (be careful with bos tokens - we need add_special_tokens=False since the chat_template already added it). +def tokenize(sample): + return tokenizer(sample["text"], padding=False, max_length=MAX_SEQUENCE_LENGTH, truncation=True, add_special_tokens=False) +ds = ds.map(tokenize, remove_columns=ds.column_names) +``` + +#### QUANTIZING THE MODEL: +```python +from llmcompressor.transformers import oneshot +from llmcompressor.modifiers.quantization import GPTQModifier + +# Configure the quantization algorithm to run. +recipe = GPTQModifier(targets="Linear", scheme="W4A16", ignore=["lm_head"], dampening_frac=0.1) + +# Apply quantization. +oneshot( + model=model, dataset=ds, + recipe=recipe, + max_seq_length=MAX_SEQUENCE_LENGTH, + num_calibration_samples=NUM_CALIBRATION_SAMPLES, +) + +# Save to disk compressed. +SAVE_DIR = "models/" + MODEL_ID.split("/")[1] + "-GPTQ-INT4" +model.save_pretrained(SAVE_DIR, max_shard_size="4GB") +tokenizer.save_pretrained(SAVE_DIR) +``` + +------ + + + + + + +## 1. Introduction + +We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. +DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. +With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. +However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, +we introduce DeepSeek-R1, which incorporates cold-start data before RL. +DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. +To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. + +**NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.** + +

+ +

+ +## 2. Model Summary + +--- + +**Post-Training: Large-Scale Reinforcement Learning on the Base Model** + +- We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area. + +- We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities. + We believe the pipeline will benefit the industry by creating better models. + +--- + +**Distillation: Smaller Models Can Be Powerful Too** + +- We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future. +- Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. + +## 3. Model Downloads + +### DeepSeek-R1 Models + +
+ +| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** | +| :------------: | :------------: | :------------: | :------------: | :------------: | +| DeepSeek-R1-Zero | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero) | +| DeepSeek-R1 | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1) | + +
+ +DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base. +For more details regarding the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository. + +### DeepSeek-R1-Distill Models + +
+ +| **Model** | **Base Model** | **Download** | +| :------------: | :------------: | :------------: | +| DeepSeek-R1-Distill-Qwen-1.5B | [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) | +| DeepSeek-R1-Distill-Qwen-7B | [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | +| DeepSeek-R1-Distill-Llama-8B | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) | +| DeepSeek-R1-Distill-Qwen-14B | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) | +|DeepSeek-R1-Distill-Qwen-32B | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) | +| DeepSeek-R1-Distill-Llama-70B | [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) | + +
+ +DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. +We slightly change their configs and tokenizers. Please use our setting to run these models. + +## 4. Evaluation Results + +### DeepSeek-R1-Evaluation + For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1. +
+ + +| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 | +|----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------| +| | Architecture | - | - | MoE | - | - | MoE | +| | # Activated Params | - | - | 37B | - | - | 37B | +| | # Total Params | - | - | 671B | - | - | 671B | +| English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 | +| | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** | +| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** | +| | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** | +| | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 | +| | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 | +| | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 | +| | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** | +| | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** | +| | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** | +| Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** | +| | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 | +| | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 | +| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 | +| | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 | +| Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** | +| | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** | +| | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** | +| Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** | +| | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** | +| | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 | + +
+ + +### Distilled Model Evaluation + + +
+ +| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating | +|------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------| +| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 | +| Claude-3.5-Sonnet-1022 | 16.0 | 26.7 | 78.3 | 65.0 | 38.9 | 717 | +| o1-mini | 63.6 | 80.0 | 90.0 | 60.0 | 53.8 | **1820** | +| QwQ-32B-Preview | 44.0 | 60.0 | 90.6 | 54.5 | 41.9 | 1316 | +| DeepSeek-R1-Distill-Qwen-1.5B | 28.9 | 52.7 | 83.9 | 33.8 | 16.9 | 954 | +| DeepSeek-R1-Distill-Qwen-7B | 55.5 | 83.3 | 92.8 | 49.1 | 37.6 | 1189 | +| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 | +| DeepSeek-R1-Distill-Qwen-32B | **72.6** | 83.3 | 94.3 | 62.1 | 57.2 | 1691 | +| DeepSeek-R1-Distill-Llama-8B | 50.4 | 80.0 | 89.1 | 49.0 | 39.6 | 1205 | +| DeepSeek-R1-Distill-Llama-70B | 70.0 | **86.7** | **94.5** | **65.2** | **57.5** | 1633 | + +
+ + +## 5. Chat Website & API Platform +You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink" + +We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/) + +## 6. How to Run Locally + +### DeepSeek-R1 Models + +Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally. + +**NOTE: Hugging Face's Transformers has not been directly supported yet.** + +### DeepSeek-R1-Distill Models + +DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models. + +For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm): + +```shell +vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager +``` + +You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang) + +```bash +python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2 +``` + +### Usage Recommendations + +**We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:** + +1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs. +2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.** +3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}." +4. When evaluating model performance, it is recommended to conduct multiple tests and average the results. + +Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting "\\n\n\") when responding to certain queries, which can adversely affect the model's performance. +**To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with "\\n" at the beginning of every output.** + +## 7. License +This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE). +DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that: +- DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1. +- DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE). +- DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE). + +## 8. Citation +``` +@misc{deepseekai2025deepseekr1incentivizingreasoningcapability, + title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, + author={DeepSeek-AI and Daya Guo and Dejian Yang and Haowei Zhang and Junxiao Song and Ruoyu Zhang and Runxin Xu and Qihao Zhu and Shirong Ma and Peiyi Wang and Xiao Bi and Xiaokang Zhang and Xingkai Yu and Yu Wu and Z. F. Wu and Zhibin Gou and Zhihong Shao and Zhuoshu Li and Ziyi Gao and Aixin Liu and Bing Xue and Bingxuan Wang and Bochao Wu and Bei Feng and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Qu and Hui Li and Jianzhong Guo and Jiashi Li and Jiawei Wang and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and J. L. Cai and Jiaqi Ni and Jian Liang and Jin Chen and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Liang Zhao and Litong Wang and Liyue Zhang and Lei Xu and Leyi Xia and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Meng Li and Miaojun Wang and Mingming Li and Ning Tian and Panpan Huang and Peng Zhang and Qiancheng Wang and Qinyu Chen and Qiushi Du and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and R. J. Chen and R. L. Jin and Ruyi Chen and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shengfeng Ye and Shiyu Wang and Shuiping Yu and Shunfeng Zhou and Shuting Pan and S. S. Li and Shuang Zhou and Shaoqing Wu and Shengfeng Ye and Tao Yun and Tian Pei and Tianyu Sun and T. Wang and Wangding Zeng and Wanjia Zhao and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and W. L. Xiao and Wei An and Xiaodong Liu and Xiaohan Wang and Xiaokang Chen and Xiaotao Nie and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and X. Q. Li and Xiangyue Jin and Xiaojin Shen and Xiaosha Chen and Xiaowen Sun and Xiaoxiang Wang and Xinnan Song and Xinyi Zhou and Xianzu Wang and Xinxia Shan and Y. K. Li and Y. Q. Wang and Y. X. Wei and Yang Zhang and Yanhong Xu and Yao Li and Yao Zhao and Yaofeng Sun and Yaohui Wang and Yi Yu and Yichao Zhang and Yifan Shi and Yiliang Xiong and Ying He and Yishi Piao and Yisong Wang and Yixuan Tan and Yiyang Ma and Yiyuan Liu and Yongqiang Guo and Yuan Ou and Yuduan Wang and Yue Gong and Yuheng Zou and Yujia He and Yunfan Xiong and Yuxiang Luo and Yuxiang You and Yuxuan Liu and Yuyang Zhou and Y. X. Zhu and Yanhong Xu and Yanping Huang and Yaohui Li and Yi Zheng and Yuchen Zhu and Yunxian Ma and Ying Tang and Yukun Zha and Yuting Yan and Z. Z. Ren and Zehui Ren and Zhangli Sha and Zhe Fu and Zhean Xu and Zhenda Xie and Zhengyan Zhang and Zhewen Hao and Zhicheng Ma and Zhigang Yan and Zhiyu Wu and Zihui Gu and Zijia Zhu and Zijun Liu and Zilin Li and Ziwei Xie and Ziyang Song and Zizheng Pan and Zhen Huang and Zhipeng Xu and Zhongyu Zhang and Zhen Zhang}, + year={2025}, + eprint={2501.12948}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2501.12948}, +} + +``` + +## 9. Contact +If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com). diff --git a/config.json b/config.json new file mode 100644 index 0000000..6779349 --- /dev/null +++ b/config.json @@ -0,0 +1,519 @@ +{ + "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": null, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": 128, + "num_bits": 4, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "group", + "symmetric": true, + "type": "int" + } + } + }, + "format": "pack-quantized", + "global_compression_ratio": 1.9011197903965849, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": { + "format": "dense", + "global_sparsity": 0.17429142138030515, + "ignore": [ + "model.layers.0.self_attn.q_proj", + "model.layers.0.self_attn.k_proj", + "model.layers.0.self_attn.v_proj", + "model.layers.0.self_attn.o_proj", + "model.layers.0.mlp.gate_proj", + "model.layers.0.mlp.up_proj", + "model.layers.0.mlp.down_proj", + "model.layers.1.self_attn.v_proj", + "model.layers.1.self_attn.o_proj", + "model.layers.2.self_attn.v_proj", + "model.layers.2.self_attn.o_proj", + "model.layers.2.mlp.up_proj", + "model.layers.3.self_attn.q_proj", + "model.layers.3.self_attn.k_proj", + "model.layers.3.self_attn.v_proj", + "model.layers.3.self_attn.o_proj", + "model.layers.3.mlp.up_proj", + "model.layers.4.self_attn.q_proj", + "model.layers.4.self_attn.k_proj", + "model.layers.4.self_attn.v_proj", + "model.layers.4.self_attn.o_proj", + "model.layers.4.mlp.gate_proj", + "model.layers.4.mlp.up_proj", + "model.layers.5.self_attn.q_proj", + "model.layers.5.self_attn.k_proj", + "model.layers.5.self_attn.v_proj", + "model.layers.5.self_attn.o_proj", + "model.layers.5.mlp.gate_proj", + "model.layers.5.mlp.up_proj", + "model.layers.5.mlp.down_proj", + "model.layers.6.self_attn.q_proj", + "model.layers.6.self_attn.k_proj", + "model.layers.6.self_attn.v_proj", + "model.layers.6.self_attn.o_proj", + "model.layers.6.mlp.gate_proj", + "model.layers.6.mlp.up_proj", + "model.layers.6.mlp.down_proj", + "model.layers.7.self_attn.q_proj", + "model.layers.7.self_attn.k_proj", + "model.layers.7.self_attn.v_proj", + "model.layers.7.self_attn.o_proj", + "model.layers.7.mlp.gate_proj", + "model.layers.7.mlp.up_proj", + "model.layers.7.mlp.down_proj", + "model.layers.8.self_attn.q_proj", + "model.layers.8.self_attn.k_proj", + "model.layers.8.self_attn.v_proj", + "model.layers.8.self_attn.o_proj", + "model.layers.8.mlp.gate_proj", + "model.layers.8.mlp.up_proj", + "model.layers.8.mlp.down_proj", + "model.layers.9.self_attn.q_proj", + "model.layers.9.self_attn.k_proj", + "model.layers.9.self_attn.v_proj", + "model.layers.9.self_attn.o_proj", + "model.layers.9.mlp.gate_proj", + "model.layers.9.mlp.up_proj", + "model.layers.9.mlp.down_proj", + "model.layers.10.self_attn.q_proj", + "model.layers.10.self_attn.k_proj", + "model.layers.10.self_attn.v_proj", + "model.layers.10.self_attn.o_proj", + "model.layers.10.mlp.gate_proj", + "model.layers.10.mlp.up_proj", + "model.layers.10.mlp.down_proj", + "model.layers.11.self_attn.q_proj", + "model.layers.11.self_attn.k_proj", + "model.layers.11.self_attn.v_proj", + "model.layers.11.self_attn.o_proj", + "model.layers.11.mlp.gate_proj", + "model.layers.11.mlp.up_proj", + "model.layers.11.mlp.down_proj", + "model.layers.12.self_attn.q_proj", + "model.layers.12.self_attn.k_proj", + "model.layers.12.self_attn.v_proj", + "model.layers.12.self_attn.o_proj", + "model.layers.12.mlp.gate_proj", + "model.layers.12.mlp.up_proj", + "model.layers.12.mlp.down_proj", + "model.layers.13.self_attn.q_proj", + "model.layers.13.self_attn.k_proj", + "model.layers.13.self_attn.v_proj", + "model.layers.13.self_attn.o_proj", + "model.layers.13.mlp.gate_proj", + "model.layers.13.mlp.up_proj", + "model.layers.13.mlp.down_proj", + "model.layers.14.self_attn.q_proj", + "model.layers.14.self_attn.k_proj", + "model.layers.14.self_attn.v_proj", + "model.layers.14.self_attn.o_proj", + "model.layers.14.mlp.gate_proj", + "model.layers.14.mlp.up_proj", + "model.layers.14.mlp.down_proj", + "model.layers.15.self_attn.q_proj", + "model.layers.15.self_attn.k_proj", + "model.layers.15.self_attn.v_proj", + "model.layers.15.self_attn.o_proj", + "model.layers.15.mlp.gate_proj", + "model.layers.15.mlp.up_proj", + "model.layers.15.mlp.down_proj", + "model.layers.16.self_attn.q_proj", + "model.layers.16.self_attn.k_proj", + "model.layers.16.self_attn.v_proj", + "model.layers.16.self_attn.o_proj", + "model.layers.16.mlp.gate_proj", + "model.layers.16.mlp.up_proj", + "model.layers.16.mlp.down_proj", + "model.layers.17.self_attn.q_proj", + "model.layers.17.self_attn.k_proj", + "model.layers.17.self_attn.v_proj", + "model.layers.17.self_attn.o_proj", + "model.layers.17.mlp.gate_proj", + "model.layers.17.mlp.up_proj", + "model.layers.17.mlp.down_proj", + "model.layers.18.self_attn.q_proj", + "model.layers.18.self_attn.k_proj", + "model.layers.18.self_attn.v_proj", + "model.layers.18.self_attn.o_proj", + "model.layers.18.mlp.gate_proj", + "model.layers.18.mlp.up_proj", + "model.layers.18.mlp.down_proj", + "model.layers.19.self_attn.q_proj", + "model.layers.19.self_attn.k_proj", + "model.layers.19.self_attn.v_proj", + "model.layers.19.self_attn.o_proj", + "model.layers.19.mlp.gate_proj", + "model.layers.19.mlp.up_proj", + "model.layers.19.mlp.down_proj", + "model.layers.20.self_attn.q_proj", + "model.layers.20.self_attn.k_proj", + "model.layers.20.self_attn.v_proj", + "model.layers.20.self_attn.o_proj", + "model.layers.20.mlp.gate_proj", + "model.layers.20.mlp.up_proj", + "model.layers.20.mlp.down_proj", + "model.layers.21.self_attn.q_proj", + "model.layers.21.self_attn.k_proj", + "model.layers.21.self_attn.v_proj", + "model.layers.21.self_attn.o_proj", + "model.layers.21.mlp.gate_proj", + "model.layers.21.mlp.up_proj", + "model.layers.21.mlp.down_proj", + "model.layers.22.self_attn.q_proj", + "model.layers.22.self_attn.k_proj", + "model.layers.22.self_attn.v_proj", + "model.layers.22.self_attn.o_proj", + "model.layers.22.mlp.gate_proj", + "model.layers.22.mlp.up_proj", + "model.layers.22.mlp.down_proj", + "model.layers.23.self_attn.q_proj", + "model.layers.23.self_attn.k_proj", + "model.layers.23.self_attn.v_proj", + "model.layers.23.self_attn.o_proj", + "model.layers.23.mlp.gate_proj", + "model.layers.23.mlp.up_proj", + "model.layers.23.mlp.down_proj", + "model.layers.24.self_attn.q_proj", + "model.layers.24.self_attn.k_proj", + "model.layers.24.self_attn.v_proj", + "model.layers.24.self_attn.o_proj", + "model.layers.24.mlp.gate_proj", + "model.layers.24.mlp.up_proj", + "model.layers.24.mlp.down_proj", + "model.layers.25.self_attn.q_proj", + "model.layers.25.self_attn.k_proj", + "model.layers.25.self_attn.v_proj", + "model.layers.25.self_attn.o_proj", + "model.layers.25.mlp.gate_proj", + "model.layers.25.mlp.up_proj", + "model.layers.25.mlp.down_proj", + "model.layers.26.self_attn.q_proj", + "model.layers.26.self_attn.k_proj", + "model.layers.26.self_attn.v_proj", + "model.layers.26.self_attn.o_proj", + "model.layers.26.mlp.gate_proj", + "model.layers.26.mlp.up_proj", + "model.layers.26.mlp.down_proj", + "model.layers.27.self_attn.q_proj", + "model.layers.27.self_attn.k_proj", + "model.layers.27.self_attn.v_proj", + "model.layers.27.self_attn.o_proj", + "model.layers.27.mlp.gate_proj", + "model.layers.27.mlp.up_proj", + "model.layers.27.mlp.down_proj", + "model.layers.28.self_attn.q_proj", + "model.layers.28.self_attn.k_proj", + "model.layers.28.self_attn.v_proj", + "model.layers.28.self_attn.o_proj", + "model.layers.28.mlp.gate_proj", + "model.layers.28.mlp.up_proj", + "model.layers.28.mlp.down_proj", + "model.layers.29.self_attn.q_proj", + "model.layers.29.self_attn.k_proj", + "model.layers.29.self_attn.v_proj", + "model.layers.29.self_attn.o_proj", + "model.layers.29.mlp.gate_proj", + "model.layers.29.mlp.up_proj", + "model.layers.29.mlp.down_proj", + "model.layers.30.self_attn.q_proj", + "model.layers.30.self_attn.k_proj", + "model.layers.30.self_attn.v_proj", + "model.layers.30.self_attn.o_proj", + "model.layers.30.mlp.gate_proj", + "model.layers.30.mlp.up_proj", + "model.layers.30.mlp.down_proj", + "model.layers.31.self_attn.q_proj", + "model.layers.31.self_attn.k_proj", + "model.layers.31.self_attn.v_proj", + "model.layers.31.self_attn.o_proj", + "model.layers.31.mlp.gate_proj", + "model.layers.31.mlp.up_proj", + "model.layers.31.mlp.down_proj", + "model.layers.32.self_attn.q_proj", + "model.layers.32.self_attn.k_proj", + "model.layers.32.self_attn.v_proj", + "model.layers.32.self_attn.o_proj", + "model.layers.32.mlp.gate_proj", + "model.layers.32.mlp.up_proj", + "model.layers.32.mlp.down_proj", + "model.layers.33.self_attn.q_proj", + "model.layers.33.self_attn.k_proj", + "model.layers.33.self_attn.v_proj", + "model.layers.33.self_attn.o_proj", + "model.layers.33.mlp.gate_proj", + "model.layers.33.mlp.up_proj", + "model.layers.33.mlp.down_proj", + "model.layers.34.self_attn.q_proj", + "model.layers.34.self_attn.k_proj", + "model.layers.34.self_attn.v_proj", + "model.layers.34.self_attn.o_proj", + "model.layers.34.mlp.gate_proj", + "model.layers.34.mlp.up_proj", + "model.layers.34.mlp.down_proj", + "model.layers.35.self_attn.q_proj", + "model.layers.35.self_attn.k_proj", + "model.layers.35.self_attn.v_proj", + "model.layers.35.self_attn.o_proj", + "model.layers.35.mlp.gate_proj", + "model.layers.35.mlp.up_proj", + "model.layers.35.mlp.down_proj", + "model.layers.36.self_attn.q_proj", + "model.layers.36.self_attn.k_proj", + "model.layers.36.self_attn.v_proj", + "model.layers.36.self_attn.o_proj", + "model.layers.36.mlp.gate_proj", + "model.layers.36.mlp.up_proj", + "model.layers.36.mlp.down_proj", + "model.layers.37.self_attn.q_proj", + "model.layers.37.self_attn.k_proj", + "model.layers.37.self_attn.v_proj", + "model.layers.37.self_attn.o_proj", + "model.layers.37.mlp.gate_proj", + "model.layers.37.mlp.up_proj", + "model.layers.37.mlp.down_proj", + "model.layers.38.self_attn.q_proj", + "model.layers.38.self_attn.k_proj", + "model.layers.38.self_attn.v_proj", + "model.layers.38.self_attn.o_proj", + "model.layers.38.mlp.gate_proj", + "model.layers.38.mlp.up_proj", + "model.layers.38.mlp.down_proj", + "model.layers.39.self_attn.q_proj", + "model.layers.39.self_attn.k_proj", + "model.layers.39.self_attn.v_proj", + "model.layers.39.self_attn.o_proj", + "model.layers.39.mlp.gate_proj", + "model.layers.39.mlp.up_proj", + "model.layers.39.mlp.down_proj", + "model.layers.40.self_attn.q_proj", + "model.layers.40.self_attn.k_proj", + "model.layers.40.self_attn.v_proj", + "model.layers.40.self_attn.o_proj", + "model.layers.40.mlp.gate_proj", + "model.layers.40.mlp.up_proj", + "model.layers.40.mlp.down_proj", + "model.layers.41.self_attn.q_proj", + "model.layers.41.self_attn.k_proj", + "model.layers.41.self_attn.v_proj", + "model.layers.41.self_attn.o_proj", + "model.layers.41.mlp.gate_proj", + "model.layers.41.mlp.up_proj", + "model.layers.41.mlp.down_proj", + "model.layers.42.self_attn.q_proj", + "model.layers.42.self_attn.k_proj", + "model.layers.42.self_attn.v_proj", + "model.layers.42.self_attn.o_proj", + "model.layers.42.mlp.gate_proj", + "model.layers.42.mlp.up_proj", + "model.layers.42.mlp.down_proj", + "model.layers.43.self_attn.q_proj", + "model.layers.43.self_attn.k_proj", + "model.layers.43.self_attn.v_proj", + "model.layers.43.self_attn.o_proj", + "model.layers.43.mlp.gate_proj", + "model.layers.43.mlp.up_proj", + "model.layers.43.mlp.down_proj", + "model.layers.44.self_attn.q_proj", + "model.layers.44.self_attn.k_proj", + "model.layers.44.self_attn.v_proj", + "model.layers.44.self_attn.o_proj", + "model.layers.44.mlp.gate_proj", + "model.layers.44.mlp.up_proj", + "model.layers.44.mlp.down_proj", + "model.layers.45.self_attn.q_proj", + "model.layers.45.self_attn.k_proj", + "model.layers.45.self_attn.v_proj", + "model.layers.45.self_attn.o_proj", + "model.layers.45.mlp.gate_proj", + "model.layers.45.mlp.up_proj", + "model.layers.45.mlp.down_proj", + "model.layers.46.self_attn.q_proj", + "model.layers.46.self_attn.k_proj", + "model.layers.46.self_attn.v_proj", + "model.layers.46.self_attn.o_proj", + "model.layers.46.mlp.gate_proj", + "model.layers.46.mlp.up_proj", + "model.layers.46.mlp.down_proj", + "model.layers.47.self_attn.q_proj", + "model.layers.47.self_attn.k_proj", + "model.layers.47.self_attn.v_proj", + "model.layers.47.self_attn.o_proj", + "model.layers.47.mlp.gate_proj", + "model.layers.47.mlp.up_proj", + "model.layers.47.mlp.down_proj", + "model.layers.48.self_attn.q_proj", + "model.layers.48.self_attn.k_proj", + "model.layers.48.self_attn.v_proj", + "model.layers.48.self_attn.o_proj", + "model.layers.48.mlp.gate_proj", + "model.layers.48.mlp.up_proj", + "model.layers.48.mlp.down_proj", + "model.layers.49.self_attn.q_proj", + "model.layers.49.self_attn.k_proj", + "model.layers.49.self_attn.v_proj", + "model.layers.49.self_attn.o_proj", + "model.layers.49.mlp.gate_proj", + "model.layers.49.mlp.up_proj", + "model.layers.49.mlp.down_proj", + "model.layers.50.self_attn.q_proj", + "model.layers.50.self_attn.k_proj", + "model.layers.50.self_attn.v_proj", + "model.layers.50.self_attn.o_proj", + "model.layers.50.mlp.gate_proj", + "model.layers.50.mlp.up_proj", + "model.layers.50.mlp.down_proj", + "model.layers.51.self_attn.q_proj", + "model.layers.51.self_attn.k_proj", + "model.layers.51.self_attn.v_proj", + "model.layers.51.self_attn.o_proj", + "model.layers.51.mlp.gate_proj", + "model.layers.51.mlp.up_proj", + "model.layers.51.mlp.down_proj", + "model.layers.52.self_attn.q_proj", + "model.layers.52.self_attn.k_proj", + "model.layers.52.self_attn.v_proj", + "model.layers.52.self_attn.o_proj", + "model.layers.52.mlp.gate_proj", + "model.layers.52.mlp.up_proj", + "model.layers.52.mlp.down_proj", + "model.layers.53.self_attn.q_proj", + "model.layers.53.self_attn.k_proj", + "model.layers.53.self_attn.v_proj", + "model.layers.53.self_attn.o_proj", + "model.layers.53.mlp.gate_proj", + "model.layers.53.mlp.up_proj", + "model.layers.53.mlp.down_proj", + "model.layers.54.self_attn.q_proj", + "model.layers.54.self_attn.k_proj", + "model.layers.54.self_attn.v_proj", + "model.layers.54.self_attn.o_proj", + "model.layers.54.mlp.gate_proj", + "model.layers.54.mlp.up_proj", + "model.layers.54.mlp.down_proj", + "model.layers.55.self_attn.q_proj", + "model.layers.55.self_attn.k_proj", + "model.layers.55.self_attn.v_proj", + "model.layers.55.self_attn.o_proj", + "model.layers.55.mlp.gate_proj", + "model.layers.55.mlp.up_proj", + "model.layers.55.mlp.down_proj", + "model.layers.56.self_attn.q_proj", + "model.layers.56.self_attn.k_proj", + "model.layers.56.self_attn.v_proj", + "model.layers.56.self_attn.o_proj", + "model.layers.56.mlp.gate_proj", + "model.layers.56.mlp.up_proj", + "model.layers.56.mlp.down_proj", + "model.layers.57.self_attn.q_proj", + "model.layers.57.self_attn.k_proj", + "model.layers.57.self_attn.v_proj", + "model.layers.57.self_attn.o_proj", + "model.layers.57.mlp.gate_proj", + "model.layers.57.mlp.up_proj", + "model.layers.57.mlp.down_proj", + "model.layers.58.self_attn.q_proj", + "model.layers.58.self_attn.k_proj", + "model.layers.58.self_attn.v_proj", + "model.layers.58.self_attn.o_proj", + "model.layers.58.mlp.gate_proj", + "model.layers.58.mlp.up_proj", + "model.layers.58.mlp.down_proj", + "model.layers.59.self_attn.q_proj", + "model.layers.59.self_attn.k_proj", + "model.layers.59.self_attn.v_proj", + "model.layers.59.self_attn.o_proj", + "model.layers.59.mlp.gate_proj", + "model.layers.59.mlp.up_proj", + "model.layers.59.mlp.down_proj", + "model.layers.60.self_attn.q_proj", + "model.layers.60.self_attn.k_proj", + "model.layers.60.self_attn.v_proj", + "model.layers.60.self_attn.o_proj", + "model.layers.60.mlp.gate_proj", + "model.layers.60.mlp.up_proj", + "model.layers.60.mlp.down_proj", + "model.layers.61.self_attn.q_proj", + "model.layers.61.self_attn.k_proj", + "model.layers.61.self_attn.v_proj", + "model.layers.61.self_attn.o_proj", + "model.layers.61.mlp.gate_proj", + "model.layers.61.mlp.up_proj", + "model.layers.61.mlp.down_proj", + "model.layers.62.self_attn.q_proj", + "model.layers.62.self_attn.k_proj", + "model.layers.62.self_attn.v_proj", + "model.layers.62.self_attn.o_proj", + "model.layers.62.mlp.gate_proj", + "model.layers.62.mlp.up_proj", + "model.layers.62.mlp.down_proj", + "model.layers.63.self_attn.q_proj", + "model.layers.63.self_attn.k_proj", + "model.layers.63.self_attn.v_proj", + "model.layers.63.self_attn.o_proj", + "model.layers.63.mlp.gate_proj", + "model.layers.63.mlp.up_proj", + "model.layers.63.mlp.down_proj", + "lm_head" + ], + "registry_requires_subclass": false, + "sparsity_structure": "unstructured", + "targets": [ + "model.layers.1.self_attn.q_proj", + "model.layers.1.self_attn.k_proj", + "model.layers.1.mlp.gate_proj", + "model.layers.1.mlp.up_proj", + "model.layers.1.mlp.down_proj", + "model.layers.2.self_attn.q_proj", + "model.layers.2.self_attn.k_proj", + "model.layers.2.mlp.gate_proj", + "model.layers.2.mlp.down_proj", + "model.layers.3.mlp.gate_proj", + "model.layers.3.mlp.down_proj", + "model.layers.4.mlp.down_proj" + ] + } + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.2", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..87dbe54 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.46.2" +} diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..1bd5a40 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f75b91680484383648aa51a75b0d65731705d8c259155a59325b4913b73f18f +size 3998627208 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..d790f51 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d717066e816927b09517eec217365dbe30022fdaaaed86423e9395f154ed613 +size 3950214888 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..cda96ce --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465914434c9e71000e361fee7ba677c0f846d16e8be7bfdf131e6bf99a863cc8 +size 3950214904 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..97534d6 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2101a63ed0ba7a10ab46369f13394c3567ca02c18897edfeacb6940138ef0dbd +size 3990749536 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..d47eb48 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ca64fb39690ea9442dbee878e8995c118136786bae57d7676bb50f7c4bd80e +size 3317298216 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..899600b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1674 @@ +{ + "metadata": { + "total_size": 19206915072 + }, + "weight_map": { + "lm_head.weight": "model-00005-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight_shape": "model-00002-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.down_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.down_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.down_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.41.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.weight_packed": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.weight_shape": "model-00003-of-00005.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.50.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.down_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.down_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.down_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.up_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.up_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.up_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.weight_packed": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.weight_scale": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.57.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.weight_shape": "model-00004-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.60.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.weight_packed": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.weight_scale": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.weight_shape": "model-00005-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00005.safetensors", + "model.norm.weight": "model-00005-of-00005.safetensors" + } +} diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..b3e0322 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,7 @@ +DEFAULT_stage: + DEFAULT_modifiers: + GPTQModifier: + dampening_frac: 0.1 + scheme: W4A16 + targets: Linear + ignore: [lm_head] diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..62b5270 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}