Upload folder using huggingface_hub

Browse files

Files changed (15) hide show

.gitattributes +1 -0
.mdl +0 -0
.msc +0 -0
.mv +1 -0
README.md +279 -0
config.json +66 -0
configuration.json +1 -0
generation_config.json +6 -0
hash.txt +2 -0
model.safetensors.index.json +910 -0
model_407-00001-of-00002.safetensors +3 -0
model_407-00002-of-00002.safetensors +3 -0
special_tokens_map.json +23 -0
tokenizer.json +3 -0
tokenizer_config.json +243 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* 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

 *.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

.mdl ADDED Viewed

Binary file (67 Bytes). View file

.msc ADDED Viewed

Binary file (850 Bytes). View file

.mv ADDED Viewed

	@@ -0,0 +1 @@


1	+ Revision:master,CreatedAt:1748534069

README.md ADDED Viewed

	@@ -0,0 +1,279 @@

+---
+frameworks:
+- Pytorch
+library_name: transformers
+license: mit
+pipeline_tag: text-generation
+base_model:
+- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+language:
+- en
+- zh
+tags:
+- Instruct
+- Chat
+- Reason Model
+- Quantization
+tools:
+- vllm
+base_model_relation: quantized
+tasks:
+- text-generation
+---
+### <span style="color:red">重要：友情提醒，推理本模型时，请按照如下官方指引：</span>
+#### 对于思考模式（enable_thinking=True， 默认为 True）
+> 请使用 Temperature=0.6 、 TopP=0.95 、 TopK=20 和 MinP=0 （ generation_config.json 中的默认设置）。请勿使用<b>贪婪解码（greedy decoding）</b>，因为它可能导致性能下降和无限循环。如需更详细的指导，请参阅最佳实践部分。
+#### 对于非思考模式（enable_thinking=False）
+> 建议使用 Temperature=0.7 、 TopP=0.8 、 TopK=20 和 MinP=0 。如需更详细的指导，请参阅最佳实践部分。
+#### 📖 关于量化损失方面的研究，可阅读公众号“觉察流”文章👇</br>
+《[Reason Model 的“瘦身计划”：量化技术的得与失](https://mp.weixin.qq.com/s/NMGq4UUkfo8GMix5LHnWCg)》
+# DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16 量化高精校准
+原模型 [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://www.modelscope.cn/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
+---
+#### _作者在此 👇🏻 扫一扫_
+<img src="https://www.modelscope.cn/models/okwinds/GPT-2/resolve/master/qrcode_for_jcl_258.jpg" />
+---
+## 下载
+SDK下载
+```bash
+#安装ModelScope
+pip install modelscope
+```
+```python
+#SDK模型下载
+from modelscope import snapshot_download
+model_dir = snapshot_download('okwinds/DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16')
+```
+Git下载
+```
+#Git模型下载
+git clone https://www.modelscope.cn/okwinds/DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16.git
+```
+## 模型概述
+DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16 是一个基于 DeepSeek-R1-0528-Qwen3-8B 的 INT4 量化并校准的模型。
+- **模型名称:** DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16
+- **模型架构:** Qwen3
+- **权重量化:** INT4
+该模型通过将 [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://www.modelscope.cn/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B) 的权重量化为 INT4 数据类型而实现。
+量化过程将每个参数从 16bit 减少到 4bit，将模型占用磁盘空间大小，以及推理时加载模型需要的GPU显存空间，减少到了大约为原模型的1/4。只有 transformer 中的 Linear 层权重是量化的，其他层均保持为原模型数据类型，采用了混合精度的计算方式，尽可能减少模型量化后所带来的精度损失。
+量化本模型，使用了[AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ)，采用 Symmetric group-wise 方式量化（group size : 128）。并在量化过程中，进行了数据校准，以提升模型生成精度。
+> <span style="color: red;">注意：本模型需要 compute capability > 8.0（Ampere、Ada Lovelace、Hopper 架构）的 Nvidia GPU 来支持 INT4 **混合精度**计算。</span>
+## 部署推理
+#### 推荐使用 vLLM>=0.8.4 ( transformers>=4.51.0 )
+Openai api 兼容模式
+```bash
+>>> vllm serve "/home/gavin/llm/DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16" --host 0.0.0.0 --port 8000 --gpu-memory-utilization 0.9 --served-model-name "DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16"
+```
+---
+# 附录 DeepSeek-R1-0528-Qwen3-8B 介绍
+# DeepSeek-R1-0528
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+<!-- markdownlint-disable no-duplicate-header -->
+<div align="center">
+  <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
+</div>
+<hr>
+<div align="center" style="line-height: 1;">
+  <a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
+    <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
+    <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+<div align="center" style="line-height: 1;">
+  <a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
+    <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
+    <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
+    <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+<div align="center" style="line-height: 1;">
+  <a href="LICENSE" style="margin: 2px;">
+    <img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+<p align="center">
+  <a href="https://arxiv.org/pdf/2501.12948"><b>Paper Link</b>👁️</a>
+</p>
+## 1. Introduction
+The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro.
+<p align="center">
+  <img width="80%" src="figures/benchmark.png">
+</p>
+Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.
+Beyond its improved reasoning capabilities, this version also offers a reduced hallucination rate, enhanced support for function calling, and better experience for vibe coding.
+## 2. Evaluation Results
+### DeepSeek-R1-0528
+ For all our models, the maximum generation length is set to 64K tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 16 responses per query to estimate pass@1.
+<div align="center">
+| Category | Benchmark (Metric)               | DeepSeek R1     | DeepSeek R1 0528
+|----------|----------------------------------|-----------------|---|
+| General  |
+|          | MMLU-Redux (EM)                   | 92.9            | 93.4
+|          | MMLU-Pro (EM)                     | 84.0            | 85.0
+|          | GPQA-Diamond (Pass@1)             | 71.5            | 81.0
+|          | SimpleQA (Correct)                | 30.1            | 27.8
+|          | FRAMES (Acc.)                     | 82.5            | 83.0
+|          | Humanity's Last Exam (Pass@1)                     | 8.5            | 17.7
+| Code |
+|          | LiveCodeBench (2408-2505) (Pass@1)        | 63.5          | 73.3
+|          | Codeforces-Div1 (Rating)          | 1530            | 1930
+|          | SWE Verified (Resolved)           | 49.2            | 57.6
+|          | Aider-Polyglot (Acc.)             | 53.3            | 71.6
+| Math |
+|          | AIME 2024 (Pass@1)                | 79.8            | 91.4
+|          | AIME 2025 (Pass@1)                     | 70.0           | 87.5
+|          | HMMT 2025 (Pass@1)            | 41.7 | 79.4 |
+|          | CNMO 2024 (Pass@1)                | 78.8            | 86.9
+| Tools |
+|          | BFCL_v3_MultiTurn (Acc)     | -            | 37.0 |
+|          | Tau-Bench   (Pass@1)       | -            | 53.5(Airline)/63.9(Retail)
+</div>
+Note: We use Agentless framework to evaluate model performance on SWE-Verified. We only evaluate text-only prompts in HLE testsets.  GPT-4.1 is employed to act user role in Tau-bench evaluation.
+### DeepSeek-R1-0528-Qwen3-8B
+Meanwhile, we distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking. We believe that the chain-of-thought from DeepSeek-R1-0528 will hold significant importance for both academic research on reasoning models and industrial development focused on small-scale models.
+|                                | AIME 24 | AIME 25 | HMMT Feb 25 | GPQA Diamond | LiveCodeBench (2408-2505) |
+|--------------------------------|---------|---------|-------------|--------------|---------------------------|
+| Qwen3-235B-A22B	                | 85.7    | 81.5    | 62.5        | 71.1         | 66.5                  |
+| Qwen3-32B                      | 81.4    | 72.9    | -           | 68.4         | -                         |
+| Qwen3-8B                      | 76.0   | 67.3    | -           | 62.0       | -                         |
+| Phi-4-Reasoning-Plus-14B       | 81.3    | 78.0    | 53.6        | 69.3         | -          |
+| Gemini-2.5-Flash-Thinking-0520 | 82.3    | 72.0    | 64.2        | 82.8         | 62.3                  |
+| o3-mini (medium)               | 79.6    | 76.7    | 53.3        | 76.8         | 65.9                     |
+| DeepSeek-R1-0528-Qwen3-8B      | 86.0   | 76.3    | 61.5        | 61.1         | 60.5                      |
+## 3. Chat Website & API Platform
+You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com/sign_in), and switch on the button "DeepThink"
+We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
+## 4. How to Run Locally
+Please visit [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) repository for more information about running DeepSeek-R1-0528 locally.
+Compared to previous versions of DeepSeek-R1, the usage recommendations for DeepSeek-R1-0528 have the following changes:
+1. System prompt is supported now.
+2. It is not required to add "\<think\>\n" at the beginning of the output to force the model into thinking pattern.
+The model architecture of DeepSeek-R1-0528-Qwen3-8B is identical to that of Qwen3-8B, but it shares the same tokenizer configuration as DeepSeek-R1-0528. This model can be run in the same manner as Qwen3-8B, but it is essential to ensure that all configuration files are sourced from our repository rather than the original Qwen3 project.
+### System Prompt
+In the official DeepSeek web/app, we use the same system prompt with a specific date.
+```
+该助手为DeepSeek-R1，由深度求索公司创造。
+今天是{current date}。
+```
+For example,
+```
+该助手为DeepSeek-R1，由深度求索公司创造。
+今天是2025年5月28日，星期一。
+```
+### Temperature
+In our web and application environments, the temperature parameter $T_{model}$ is set to 0.6.
+### Prompts for File Uploading and Web Search
+For file uploading, please follow the template to create prompts, where {file_name}, {file_content} and {question} are arguments.
+```
+file_template = \
+"""[file name]: {file_name}
+[file content begin]
+{file_content}
+[file content end]
+{question}"""
+```
+For Web Search, {search_results}, {cur_date}, and {question} are arguments.
+For Chinese query, we use the prompt:
+```
+search_answer_zh_template = \
+'''# 以下内容是基于用户发送的消息的搜索结果:
+{search_results}
+在我给你的搜索结果中，每个结果都是[webpage X begin]...[webpage X end]格式的，X代表每篇文章的数字索引。请在适当的情况下在句子末尾引用上下文。请按照引用编号[citation:X]的格式在答案中对应部分引用上下文。如果一句话源自多个上下文，请列出所有相关的引用编号，例如[citation:3][citation:5]，切记不要将引用集中在最后返回引用编号，而是在答案对应部分列出。
+在回答时，请注意以下几点：
+- 今天是{cur_date}。
+- 并非搜索结果的所有内容都与用户的问题密切相关，你需要结合问题，对搜索结果进行甄别、筛选。
+- 对于列举类的问题（如列举所有航班信息），尽量将答案控制在10个要点以内，并告诉用户可以查看搜索来源、获得完整信息。优先提供信息完整、最相关的列举项；如非必要，不要主动告诉用户搜索结果未提供的内容。
+- 对于创作类的问题（如写论文），请务必在正文的段落中引用对应的参考编号，例如[citation:3][citation:5]，不能只在文章末尾引用。你需要解读并概括用户的题目要求，选择合适的格式，充分利用搜索结果并抽取重要信息，生成符合用户要求、极具思想深度、富有创造力与专业性的答案。你的创作篇幅需要尽可能延长，对于每一个要点的论述要推测用户的意图，给出尽可能多角度的回答要点，且务必信息量大、论述详尽。
+- 如果回答很长，请尽量结构化、分段落总结。如果需要分点作答，尽量控制在5个点以内，并合并相关的内容。
+- 对于客观类的问答，如果问题的答案非常简短，可以适当补充一到两句相关信息，以丰富内容。
+- 你需要根据用户要求和回答内容选择合适、美观的回答格式，确保可读性强。
+- 你的回答应该综合多个相关网页来回答，不能重复引用一个网页。
+- 除非用户要求，否则你回答的语言需要和用户提问的语言保持一致。
+# 用户消息为：
+{question}'''
+```
+For English query, we use the prompt:
+```
+search_answer_en_template = \
+'''# The following contents are the search results related to the user's message:
+{search_results}
+In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
+When responding, please keep the following points in mind:
+- Today is {cur_date}.
+- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
+- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
+- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
+- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
+- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
+- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
+- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
+- Unless the user requests otherwise, your response should be in the same language as the user's question.
+# The user's message is:
+{question}'''
+```

config.json ADDED Viewed

	@@ -0,0 +1,66 @@

+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "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": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "attn_factor": 0.8782488562869419,
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn"
+  },
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"framework":"Pytorch","task":"text-generation"}

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.51.3"
+}

hash.txt ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ f0d738f36bb997b9a11db44b3365cef257054f5406577407300fdecf66cbea36 model_407-00001-of-00002.safetensors
2	+ 9bdb0a536e6049f478b10a4f5499e59882feecdba779352c353c25a344f166ac model_407-00002-of-00002.safetensors

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,910 @@

+{
+  "metadata": {
+    "total_size": 6071351232
+  },
+  "weight_map": {
+    "lm_head.weight": "model_407-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_packed": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_scale": "model_407-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_shape": "model_407-00001-of-00002.safetensors",
+    "model.norm.weight": "model_407-00001-of-00002.safetensors"
+  }
+}

model_407-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d738f36bb997b9a11db44b3365cef257054f5406577407300fdecf66cbea36
+size 4826794352

model_407-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdb0a536e6049f478b10a4f5499e59882feecdba779352c353c25a344f166ac
+size 1244659840

special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8496719b340ee4a57f73a2b132b686c06d66be815a28fba73acfaa8830eb0b
+size 11424039

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,243 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151670": {
+      "content": "<｜Assistant｜>",
+      "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='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- 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｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}