初始化项目，由ModelHub XC社区提供模型

Model: QuantTrio/KAT-Dev-GPTQ-Int4
Source: Original Platform

.gitattributes

@@ -0,0 +1,56 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+merges.txt filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,158 @@
+---
+language:
+  - multilingual
+license: apache-2.0
+license_name: kwaipilot-license
+license_link: LICENSE
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- GPTQ
+- Int4
+- vLLM
+base_model:
+  - Kwaipilot/KAT-Dev
+base_model_relation: quantized
+---
+# KAT-Dev-GPTQ-Int4
+Base model: [Kwaipilot/KAT-Dev](https://huggingface.co/Kwaipilot/KAT-Dev)
+
+<i>Calibrate using the https://huggingface.co/datasets/timdettmers/openassistant-guanaco/blob/main/openassistant_best_replies_eval.jsonl dataset.</i>
+<br>
+<i>The quantization configuration is as follows</i>
+
+```
+quant_config = QuantizeConfig(bits=4, group_size=128, desc_act=False)
+```
+
+### 【vLLM Startup Command】
+```
+vllm serve JunHowie/KAT-Dev-GPTQ-Int4 
+```
+
+### 【Dependencies】
+```
+vllm>=0.10.2
+transformers>=4.56.1
+```
+
+### 【Model Download】
+
+```python
+from huggingface_hub import snapshot_download
+snapshot_download('JunHowie/KAT-Dev-GPTQ-Int4', cache_dir="your_local_path")
+```
+
+### 【Overview】
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/61ee40a269351366e29972ad/KIYEa1c_WJEWPpeS0L_k1.png" width="100%" alt="Kwaipilot" />
+</div>
+
+<hr>
+
+
+# News
+
+🔥 We’re thrilled to announce the release of KAT-Dev-72B-Exp, our latest and most powerful model yet!
+
+🔥 You can now try our **strongest** proprietary coder model **KAT-Coder** directly on the [StreamLake](https://www.streamlake.ai/product/kat-coder) platform **for free**.
+
+# Highlights
+**KAT-Dev-32B**  is an open-source 32B-parameter model for software engineering tasks.
+
+On SWE-Bench Verified, **KAT-Dev-32B** achieves comparable performance with **62.4%** resolved and ranks **5th** among all open-source models with different scales.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61ee40a269351366e29972ad/dTpQQPQnp1TdD4YB8gZAu.png)
+
+# Introduction
+
+**KAT-Dev-32B** is optimized via several stages of training, including a mid-training stage, supervised fine-tuning (SFT) & reinforcement fine-tuning (RFT) stage and an large-scale agentic reinforcement learning (RL) stage. In summary, our contributions include:
+ 
+<table>
+  <thead>
+    <tr>
+      <th style="text-align:left; width:18%;">Stage</th>
+      <th style="text-align:left;">Key Techniques</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><strong>1. Mid-Training</strong></td>
+      <td>We observe that adding extensive training for tool-use capability, multi-turn interaction, and instruction-following at this stage may not yield large performance gains in the current results (e.g., on leaderboards like SWE-bench). However, since our experiments are based on the Qwen3-32B model, we find that enhancing these foundational capabilities will have a significant impact on the subsequent SFT and RL stages. This suggests that improving such core abilities can profoundly influence the model’s capacity to handle more complex tasks.
+</td>
+    </tr>
+    <tr>
+      <td><strong>2. SFT & RFT</strong></td>
+      <td>We meticulously curated eight task types and eight programming scenarios during the SFT stage to ensure the model’s generalization and comprehensive capabilities. Moreover, before RL, we innovatively introduced an RFT stage. Compared with traditional RL, we incorporate “teacher trajectories” annotated by human engineers as guidance during training—much like a learner driver being assisted by an experienced co-driver before officially driving after getting a license. This step not only boosts model performance but also further stabilizes the subsequent RL training.
+</td>
+    </tr>
+    <tr>
+      <td><strong>3. Agentic RL Scaling</strong></td>
+      <td>Scaling agentic RL hinges on three challenges: efficient learning over nonlinear trajectory histories, leveraging intrinsic model signals, and building scalable high-throughput infrastructure. We address these with a multi-level prefix caching mechanism in the RL training engine, an entropy-based trajectory pruning technique, and an inner implementation of SeamlessFlow[1] architecture that cleanly decouples agents from training while exploiting heterogeneous compute. These innovations together cut scaling costs and enable efficient large-scale RL.
+</td>
+    </tr>
+  </tbody>
+</table>
+
+For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://kwaipilot.github.io/KAT-Coder/).
+
+# Quickstart
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Kwaipilot/KAT-Dev"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=65536
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+print("content:", content)
+```
+
+## Claude Code
+ ### vllm server
+```
+MODEL_PATH="Kwaipilot/KAT-Dev"
+
+vllm serve $MODEL_PATH \
+      --enable-prefix-caching \
+      --tensor-parallel-size 8 \
+      --tool-parser-plugin $MODEL_PATH/qwen3coder_tool_parser.py \
+      --chat-template $MODEL_PATH/chat_template.jinja \
+      --enable-auto-tool-choice --tool-call-parser qwen3_coder
+```
+
+[claude-code-router](https://github.com/musistudio/claude-code-router) is a third-party routing utility that allows Claude Code to flexibly switch between different backend APIs.  
+On the dashScope platform, you can install the **claude-code-config** extension package, which automatically generates a default configuration for `claude-code-router` with built-in dashScope support.
+
+Once the configuration files and plugin directory are generated, the environment required by `ccr` will be ready.  
+If needed, you can still manually edit `~/.claude-code-router/config.json` and the files under `~/.claude-code-router/plugins/` to customize the setup.
+
+Finally, simply start `ccr` to run Claude Code and seamlessly connect it with the powerful coding capabilities of **KAT-Dev-32B**.  
+Happy coding!

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,120 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": false,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.05,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:4.2.5"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "v2": false,
+      "v2_alpha": 0.25
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3ce822b5879263d052dd03fa1eff2f07a60f3ea83b8869936d110e7e5c21f8
+size 3955280848

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a423076e328bbfb7ec6ac84e10a63a868637ab4c8b6d4037e4428b970b572f
+size 3989151776

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f996f378c1b5382a28a914a25fa2889f49aafdd582d6c1a8994811f61ee51d9
+size 3939923288

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7221ada0047e6151d3e31af16af04a58f66a85214c48b9a6fd689f65305e9bb
+size 3989151824

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2391b141b28b8201111096b54bac87a47c45cfded1379deacf8e6073e126b3
+size 3467226552

quant_log.csv

@@ -0,0 +1,449 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.0000000162,0.05000,3.234
+0,self_attn.v_proj,0.0000000127,0.05000,1.044
+0,self_attn.q_proj,0.0000000816,0.05000,1.081
+0,self_attn.o_proj,0.0000004007,0.05000,1.772
+0,mlp.gate_proj,0.0000024797,0.05000,1.139
+0,mlp.up_proj,0.0000021738,0.05000,1.122
+0,mlp.down_proj,0.0000023848,0.05000,8.001
+1,self_attn.k_proj,0.0000000269,0.05000,1.034
+1,self_attn.v_proj,0.0000000269,0.05000,1.033
+1,self_attn.q_proj,0.0000001541,0.05000,1.057
+1,self_attn.o_proj,0.0000002456,0.05000,2.065
+1,mlp.gate_proj,0.0001649253,0.05000,1.130
+1,mlp.up_proj,0.0000509813,0.05000,1.139
+1,mlp.down_proj,0.0000078315,0.05000,8.037
+2,self_attn.k_proj,0.0000000458,0.05000,1.044
+2,self_attn.v_proj,0.0000000446,0.05000,1.042
+2,self_attn.q_proj,0.0000002448,0.05000,1.073
+2,self_attn.o_proj,0.0000004594,0.05000,1.767
+2,mlp.gate_proj,0.0002349929,0.05000,1.133
+2,mlp.up_proj,0.0000981800,0.05000,1.123
+2,mlp.down_proj,0.0000073423,0.05000,8.280
+3,self_attn.k_proj,0.0000000833,0.05000,1.046
+3,self_attn.v_proj,0.0000000865,0.05000,1.036
+3,self_attn.q_proj,0.0000004506,0.05000,1.061
+3,self_attn.o_proj,0.0000004512,0.05000,1.760
+3,mlp.gate_proj,0.0003456217,0.05000,1.165
+3,mlp.up_proj,0.0001514415,0.05000,1.139
+3,mlp.down_proj,0.0000142816,0.05000,8.122
+4,self_attn.k_proj,0.0000001313,0.05000,1.087
+4,self_attn.v_proj,0.0000001358,0.05000,1.077
+4,self_attn.q_proj,0.0000007362,0.05000,1.086
+4,self_attn.o_proj,0.0000006806,0.05000,1.787
+4,mlp.gate_proj,0.0004579198,0.05000,1.393
+4,mlp.up_proj,0.0002564290,0.05000,1.235
+4,mlp.down_proj,0.0000159178,0.05000,8.022
+5,self_attn.k_proj,0.0000001601,0.05000,1.057
+5,self_attn.v_proj,0.0000001558,0.05000,1.053
+5,self_attn.q_proj,0.0000008758,0.05000,1.111
+5,self_attn.o_proj,0.0000006760,0.05000,1.793
+5,mlp.gate_proj,0.0005507642,0.05000,1.163
+5,mlp.up_proj,0.0002391874,0.05000,1.142
+5,mlp.down_proj,0.0000223429,0.05000,7.979
+6,self_attn.k_proj,0.0000001918,0.05000,1.062
+6,self_attn.v_proj,0.0000002022,0.05000,1.049
+6,self_attn.q_proj,0.0000011141,0.05000,1.076
+6,self_attn.o_proj,0.0000007390,0.05000,1.766
+6,mlp.gate_proj,0.0009107982,0.05000,1.126
+6,mlp.up_proj,0.0005256533,0.05000,1.121
+6,mlp.down_proj,0.0043096024,0.05000,7.967
+7,self_attn.k_proj,0.0000011770,0.05000,1.037
+7,self_attn.v_proj,0.0000012232,0.05000,1.034
+7,self_attn.q_proj,0.0000069287,0.05000,1.058
+7,self_attn.o_proj,0.0000025039,0.05000,1.751
+7,mlp.gate_proj,0.0009953627,0.05000,1.117
+7,mlp.up_proj,0.0005493904,0.05000,1.125
+7,mlp.down_proj,0.0000297612,0.05000,7.977
+8,self_attn.k_proj,0.0000010946,0.05000,1.069
+8,self_attn.v_proj,0.0000011919,0.05000,1.056
+8,self_attn.q_proj,0.0000061875,0.05000,1.069
+8,self_attn.o_proj,0.0000025796,0.05000,1.768
+8,mlp.gate_proj,0.0002623779,0.05000,1.124
+8,mlp.up_proj,0.0001344016,0.05000,1.116
+8,mlp.down_proj,0.0000189611,0.05000,7.998
+9,self_attn.k_proj,0.0000006171,0.05000,1.059
+9,self_attn.v_proj,0.0000006324,0.05000,1.072
+9,self_attn.q_proj,0.0000033820,0.05000,1.084
+9,self_attn.o_proj,0.0000015995,0.05000,1.779
+9,mlp.gate_proj,0.0001099972,0.05000,1.142
+9,mlp.up_proj,0.0001023062,0.05000,1.150
+9,mlp.down_proj,0.0000218911,0.05000,7.992
+10,self_attn.k_proj,0.0000009853,0.05000,1.044
+10,self_attn.v_proj,0.0000011111,0.05000,1.036
+10,self_attn.q_proj,0.0000058205,0.05000,1.061
+10,self_attn.o_proj,0.0000031338,0.05000,1.750
+10,mlp.gate_proj,0.0001112629,0.05000,1.220
+10,mlp.up_proj,0.0001056672,0.05000,1.115
+10,mlp.down_proj,0.0000184607,0.05000,8.407
+11,self_attn.k_proj,0.0000013373,0.05000,1.040
+11,self_attn.v_proj,0.0000014252,0.05000,1.057
+11,self_attn.q_proj,0.0000076782,0.05000,1.102
+11,self_attn.o_proj,0.0000045550,0.05000,1.756
+11,mlp.gate_proj,0.0001260963,0.05000,1.126
+11,mlp.up_proj,0.0001195048,0.05000,1.119
+11,mlp.down_proj,0.0000218171,0.05000,8.003
+12,self_attn.k_proj,0.0000009299,0.05000,1.044
+12,self_attn.v_proj,0.0000010058,0.05000,1.041
+12,self_attn.q_proj,0.0000054316,0.05000,1.077
+12,self_attn.o_proj,0.0000024059,0.05000,1.766
+12,mlp.gate_proj,0.0001412866,0.05000,1.116
+12,mlp.up_proj,0.0001323689,0.05000,1.117
+12,mlp.down_proj,0.0000244210,0.05000,7.955
+13,self_attn.k_proj,0.0000017760,0.05000,1.062
+13,self_attn.v_proj,0.0000018995,0.05000,1.051
+13,self_attn.q_proj,0.0000102478,0.05000,1.079
+13,self_attn.o_proj,0.0000036599,0.05000,1.810
+13,mlp.gate_proj,0.0001465452,0.05000,1.188
+13,mlp.up_proj,0.0001332961,0.05000,1.174
+13,mlp.down_proj,0.0000243287,0.05000,8.004
+14,self_attn.k_proj,0.0000009200,0.05000,1.052
+14,self_attn.v_proj,0.0000009821,0.05000,1.049
+14,self_attn.q_proj,0.0000048295,0.05000,1.076
+14,self_attn.o_proj,0.0000034132,0.05000,1.790
+14,mlp.gate_proj,0.0001352126,0.05000,1.166
+14,mlp.up_proj,0.0001249658,0.05000,1.125
+14,mlp.down_proj,0.0000223208,0.05000,8.035
+15,self_attn.k_proj,0.0000008635,0.05000,1.041
+15,self_attn.v_proj,0.0000009282,0.05000,1.048
+15,self_attn.q_proj,0.0000051504,0.05000,1.069
+15,self_attn.o_proj,0.0000034768,0.05000,1.808
+15,mlp.gate_proj,0.0001202492,0.05000,1.134
+15,mlp.up_proj,0.0001143246,0.05000,1.126
+15,mlp.down_proj,0.0000198175,0.05000,7.997
+16,self_attn.k_proj,0.0000008311,0.05000,1.044
+16,self_attn.v_proj,0.0000009154,0.05000,1.044
+16,self_attn.q_proj,0.0000048815,0.05000,1.071
+16,self_attn.o_proj,0.0000034149,0.05000,1.769
+16,mlp.gate_proj,0.0001051558,0.05000,1.122
+16,mlp.up_proj,0.0001000832,0.05000,1.120
+16,mlp.down_proj,0.0000178747,0.05000,7.986
+17,self_attn.k_proj,0.0000008668,0.05000,1.065
+17,self_attn.v_proj,0.0000008656,0.05000,1.034
+17,self_attn.q_proj,0.0000049575,0.05000,1.060
+17,self_attn.o_proj,0.0000033593,0.05000,1.801
+17,mlp.gate_proj,0.0001086903,0.05000,1.307
+17,mlp.up_proj,0.0001033014,0.05000,1.149
+17,mlp.down_proj,0.0000185236,0.05000,8.088
+18,self_attn.k_proj,0.0000011330,0.05000,1.038
+18,self_attn.v_proj,0.0000011757,0.05000,1.035
+18,self_attn.q_proj,0.0000066043,0.05000,1.060
+18,self_attn.o_proj,0.0000032982,0.05000,1.778
+18,mlp.gate_proj,0.0001154338,0.05000,1.132
+18,mlp.up_proj,0.0001092103,0.05000,1.119
+18,mlp.down_proj,0.0000206254,0.05000,8.189
+19,self_attn.k_proj,0.0000012775,0.05000,1.064
+19,self_attn.v_proj,0.0000013057,0.05000,1.055
+19,self_attn.q_proj,0.0000077177,0.05000,1.096
+19,self_attn.o_proj,0.0000044452,0.05000,1.800
+19,mlp.gate_proj,0.0001260705,0.05000,1.486
+19,mlp.up_proj,0.0001200554,0.05000,1.139
+19,mlp.down_proj,0.0000240489,0.05000,8.030
+20,self_attn.k_proj,0.0000021487,0.05000,1.063
+20,self_attn.v_proj,0.0000023166,0.05000,1.042
+20,self_attn.q_proj,0.0000125007,0.05000,1.071
+20,self_attn.o_proj,0.0000046935,0.05000,1.767
+20,mlp.gate_proj,0.0001376763,0.05000,1.140
+20,mlp.up_proj,0.0001314726,0.05000,1.122
+20,mlp.down_proj,0.0000271172,0.05000,7.966
+21,self_attn.k_proj,0.0000024297,0.05000,1.054
+21,self_attn.v_proj,0.0000025375,0.05000,1.049
+21,self_attn.q_proj,0.0000141194,0.05000,1.082
+21,self_attn.o_proj,0.0000085868,0.05000,1.793
+21,mlp.gate_proj,0.0001451987,0.05000,1.146
+21,mlp.up_proj,0.0001385588,0.05000,1.146
+21,mlp.down_proj,0.0000308469,0.05000,8.023
+22,self_attn.k_proj,0.0000021045,0.05000,1.048
+22,self_attn.v_proj,0.0000022902,0.05000,1.063
+22,self_attn.q_proj,0.0000127400,0.05000,1.062
+22,self_attn.o_proj,0.0000103736,0.05000,1.779
+22,mlp.gate_proj,0.0001592715,0.05000,1.118
+22,mlp.up_proj,0.0001518224,0.05000,1.117
+22,mlp.down_proj,0.0000371563,0.05000,7.971
+23,self_attn.k_proj,0.0000029360,0.05000,1.048
+23,self_attn.v_proj,0.0000033406,0.05000,1.038
+23,self_attn.q_proj,0.0000168955,0.05000,1.065
+23,self_attn.o_proj,0.0000069991,0.05000,1.822
+23,mlp.gate_proj,0.0001751471,0.05000,1.119
+23,mlp.up_proj,0.0001665793,0.05000,1.115
+23,mlp.down_proj,0.0000446570,0.05000,7.956
+24,self_attn.k_proj,0.0000052270,0.05000,1.056
+24,self_attn.v_proj,0.0000058457,0.05000,1.063
+24,self_attn.q_proj,0.0000323477,0.05000,1.082
+24,self_attn.o_proj,0.0000152148,0.05000,1.768
+24,mlp.gate_proj,0.0001969212,0.05000,1.136
+24,mlp.up_proj,0.0001863398,0.05000,1.122
+24,mlp.down_proj,0.0000521306,0.05000,8.003
+25,self_attn.k_proj,0.0000045368,0.05000,1.051
+25,self_attn.v_proj,0.0000049879,0.05000,1.045
+25,self_attn.q_proj,0.0000270423,0.05000,1.071
+25,self_attn.o_proj,0.0000139668,0.05000,1.761
+25,mlp.gate_proj,0.0002213674,0.05000,1.138
+25,mlp.up_proj,0.0002081905,0.05000,1.123
+25,mlp.down_proj,0.0000665647,0.05000,8.044
+26,self_attn.k_proj,0.0000041029,0.05000,1.053
+26,self_attn.v_proj,0.0000047737,0.05000,1.059
+26,self_attn.q_proj,0.0000243842,0.05000,1.070
+26,self_attn.o_proj,0.0000125715,0.05000,1.760
+26,mlp.gate_proj,0.0002470852,0.05000,1.130
+26,mlp.up_proj,0.0002283383,0.05000,1.125
+26,mlp.down_proj,0.0000837923,0.05000,8.451
+27,self_attn.k_proj,0.0000060690,0.05000,1.064
+27,self_attn.v_proj,0.0000072178,0.05000,1.058
+27,self_attn.q_proj,0.0000348095,0.05000,1.088
+27,self_attn.o_proj,0.0000136795,0.05000,1.776
+27,mlp.gate_proj,0.0002878364,0.05000,1.129
+27,mlp.up_proj,0.0002608704,0.05000,1.129
+27,mlp.down_proj,0.0001052239,0.05000,8.030
+28,self_attn.k_proj,0.0000077865,0.05000,1.051
+28,self_attn.v_proj,0.0000093256,0.05000,1.052
+28,self_attn.q_proj,0.0000463542,0.05000,1.075
+28,self_attn.o_proj,0.0000149359,0.05000,1.786
+28,mlp.gate_proj,0.0003251187,0.05000,1.134
+28,mlp.up_proj,0.0002960902,0.05000,1.120
+28,mlp.down_proj,0.0001167624,0.05000,7.985
+29,self_attn.k_proj,0.0000116028,0.05000,1.046
+29,self_attn.v_proj,0.0000124041,0.05000,1.043
+29,self_attn.q_proj,0.0000637293,0.05000,1.073
+29,self_attn.o_proj,0.0000136918,0.05000,1.772
+29,mlp.gate_proj,0.0003617665,0.05000,1.127
+29,mlp.up_proj,0.0003126921,0.05000,1.123
+29,mlp.down_proj,0.0001199714,0.05000,7.968
+30,self_attn.k_proj,0.0000238225,0.05000,1.046
+30,self_attn.v_proj,0.0000317723,0.05000,1.045
+30,self_attn.q_proj,0.0001267295,0.05000,1.081
+30,self_attn.o_proj,0.0000166787,0.05000,1.776
+30,mlp.gate_proj,0.0006058461,0.05000,1.123
+30,mlp.up_proj,0.0003959458,0.05000,1.121
+30,mlp.down_proj,0.0001081030,0.05000,8.004
+31,self_attn.k_proj,0.0000196001,0.05000,1.059
+31,self_attn.v_proj,0.0000222575,0.05000,1.054
+31,self_attn.q_proj,0.0001011776,0.05000,1.075
+31,self_attn.o_proj,0.0000166730,0.05000,1.782
+31,mlp.gate_proj,0.0010467220,0.05000,1.145
+31,mlp.up_proj,0.0007263806,0.05000,1.148
+31,mlp.down_proj,0.0001074331,0.05000,8.376
+32,self_attn.k_proj,0.0000057730,0.05000,1.069
+32,self_attn.v_proj,0.0000073269,0.05000,1.055
+32,self_attn.q_proj,0.0000331176,0.05000,1.088
+32,self_attn.o_proj,0.0000133086,0.05000,1.784
+32,mlp.gate_proj,0.0005488825,0.05000,1.131
+32,mlp.up_proj,0.0003933588,0.05000,1.135
+32,mlp.down_proj,0.0001048277,0.05000,8.001
+33,self_attn.k_proj,0.0000048959,0.05000,1.042
+33,self_attn.v_proj,0.0000050340,0.05000,1.052
+33,self_attn.q_proj,0.0000268427,0.05000,1.084
+33,self_attn.o_proj,0.0000099646,0.05000,1.772
+33,mlp.gate_proj,0.0003607540,0.05000,1.121
+33,mlp.up_proj,0.0003298347,0.05000,1.118
+33,mlp.down_proj,0.0001057911,0.05000,7.965
+34,self_attn.k_proj,0.0000065684,0.05000,1.047
+34,self_attn.v_proj,0.0000074894,0.05000,1.048
+34,self_attn.q_proj,0.0000404844,0.05000,1.081
+34,self_attn.o_proj,0.0000151833,0.05000,1.776
+34,mlp.gate_proj,0.0003230668,0.05000,1.140
+34,mlp.up_proj,0.0003079835,0.05000,1.126
+34,mlp.down_proj,0.0000838736,0.05000,8.001
+35,self_attn.k_proj,0.0000077875,0.05000,1.044
+35,self_attn.v_proj,0.0000089657,0.05000,1.038
+35,self_attn.q_proj,0.0000481206,0.05000,1.079
+35,self_attn.o_proj,0.0000184487,0.05000,1.764
+35,mlp.gate_proj,0.0003501297,0.05000,1.120
+35,mlp.up_proj,0.0003335290,0.05000,1.125
+35,mlp.down_proj,0.0000936887,0.05000,8.692
+36,self_attn.k_proj,0.0000049325,0.05000,1.043
+36,self_attn.v_proj,0.0000056771,0.05000,1.044
+36,self_attn.q_proj,0.0000304468,0.05000,1.072
+36,self_attn.o_proj,0.0000143740,0.05000,3.903
+36,mlp.gate_proj,0.0003720354,0.05000,1.124
+36,mlp.up_proj,0.0003543600,0.05000,1.118
+36,mlp.down_proj,0.0001041509,0.05000,8.588
+37,self_attn.k_proj,0.0000100719,0.05000,1.054
+37,self_attn.v_proj,0.0000115485,0.05000,1.049
+37,self_attn.q_proj,0.0000616053,0.05000,1.209
+37,self_attn.o_proj,0.0000252617,0.05000,1.812
+37,mlp.gate_proj,0.0003926754,0.05000,1.200
+37,mlp.up_proj,0.0003614664,0.05000,1.117
+37,mlp.down_proj,0.0001064732,0.05000,7.987
+38,self_attn.k_proj,0.0000067528,0.05000,1.065
+38,self_attn.v_proj,0.0000076714,0.05000,1.060
+38,self_attn.q_proj,0.0000400771,0.05000,1.181
+38,self_attn.o_proj,0.0000220664,0.05000,1.787
+38,mlp.gate_proj,0.0003429898,0.05000,1.140
+38,mlp.up_proj,0.0003293061,0.05000,1.142
+38,mlp.down_proj,0.0001008956,0.05000,8.009
+39,self_attn.k_proj,0.0000061872,0.05000,1.069
+39,self_attn.v_proj,0.0000065399,0.05000,1.068
+39,self_attn.q_proj,0.0000380468,0.05000,1.078
+39,self_attn.o_proj,0.0000231821,0.05000,1.772
+39,mlp.gate_proj,0.0003072655,0.05000,1.135
+39,mlp.up_proj,0.0003144672,0.05000,1.128
+39,mlp.down_proj,0.0000982053,0.05000,8.046
+40,self_attn.k_proj,0.0000075060,0.05000,1.053
+40,self_attn.v_proj,0.0000085450,0.05000,1.047
+40,self_attn.q_proj,0.0000463455,0.05000,1.099
+40,self_attn.o_proj,0.0000311977,0.05000,1.764
+40,mlp.gate_proj,0.0002644811,0.05000,1.130
+40,mlp.up_proj,0.0002856952,0.05000,1.126
+40,mlp.down_proj,0.0000964624,0.05000,7.991
+41,self_attn.k_proj,0.0000073851,0.05000,1.042
+41,self_attn.v_proj,0.0000080522,0.05000,1.045
+41,self_attn.q_proj,0.0000478026,0.05000,1.070
+41,self_attn.o_proj,0.0000302376,0.05000,1.768
+41,mlp.gate_proj,0.0002724422,0.05000,1.130
+41,mlp.up_proj,0.0002986726,0.05000,1.111
+41,mlp.down_proj,0.0000970860,0.05000,7.992
+42,self_attn.k_proj,0.0000100851,0.05000,1.056
+42,self_attn.v_proj,0.0000115108,0.05000,1.053
+42,self_attn.q_proj,0.0000662501,0.05000,1.090
+42,self_attn.o_proj,0.0000333506,0.05000,1.782
+42,mlp.gate_proj,0.0002813541,0.05000,1.348
+42,mlp.up_proj,0.0003163875,0.05000,1.161
+42,mlp.down_proj,0.0001026058,0.05000,8.362
+43,self_attn.k_proj,0.0000145322,0.05000,1.050
+43,self_attn.v_proj,0.0000158925,0.05000,1.048
+43,self_attn.q_proj,0.0000893748,0.05000,1.075
+43,self_attn.o_proj,0.0000389413,0.05000,1.763
+43,mlp.gate_proj,0.0003090515,0.05000,1.137
+43,mlp.up_proj,0.0003404725,0.05000,1.119
+43,mlp.down_proj,0.0002586559,0.05000,7.994
+44,self_attn.k_proj,0.0000218219,0.05000,1.054
+44,self_attn.v_proj,0.0000259004,0.05000,1.055
+44,self_attn.q_proj,0.0001479396,0.05000,1.077
+44,self_attn.o_proj,0.0000474695,0.05000,1.783
+44,mlp.gate_proj,0.0003127389,0.05000,1.128
+44,mlp.up_proj,0.0003464879,0.05000,1.124
+44,mlp.down_proj,0.0001232855,0.05000,8.231
+45,self_attn.k_proj,0.0000227116,0.05000,1.042
+45,self_attn.v_proj,0.0000225401,0.05000,1.042
+45,self_attn.q_proj,0.0001326203,0.05000,1.096
+45,self_attn.o_proj,0.0000609935,0.05000,1.758
+45,mlp.gate_proj,0.0003154614,0.05000,1.142
+45,mlp.up_proj,0.0003421955,0.05000,1.125
+45,mlp.down_proj,0.0001295402,0.05000,8.166
+46,self_attn.k_proj,0.0000203155,0.05000,1.042
+46,self_attn.v_proj,0.0000243960,0.05000,1.040
+46,self_attn.q_proj,0.0001327600,0.05000,1.074
+46,self_attn.o_proj,0.0000586457,0.05000,1.758
+46,mlp.gate_proj,0.0003317181,0.05000,1.153
+46,mlp.up_proj,0.0003596539,0.05000,1.137
+46,mlp.down_proj,0.0001373474,0.05000,7.975
+47,self_attn.k_proj,0.0000287401,0.05000,1.059
+47,self_attn.v_proj,0.0000378734,0.05000,1.049
+47,self_attn.q_proj,0.0001960034,0.05000,1.094
+47,self_attn.o_proj,0.0000479580,0.05000,1.804
+47,mlp.gate_proj,0.0003378080,0.05000,1.130
+47,mlp.up_proj,0.0003639913,0.05000,1.130
+47,mlp.down_proj,0.0001630509,0.05000,8.682
+48,self_attn.k_proj,0.0000326587,0.05000,1.070
+48,self_attn.v_proj,0.0000420830,0.05000,1.069
+48,self_attn.q_proj,0.0002336485,0.05000,1.089
+48,self_attn.o_proj,0.0000797854,0.05000,1.795
+48,mlp.gate_proj,0.0003719960,0.05000,1.677
+48,mlp.up_proj,0.0003905721,0.05000,1.151
+48,mlp.down_proj,0.0001752929,0.05000,8.103
+49,self_attn.k_proj,0.0000346826,0.05000,1.048
+49,self_attn.v_proj,0.0000406586,0.05000,1.054
+49,self_attn.q_proj,0.0002300940,0.05000,1.088
+49,self_attn.o_proj,0.0000726788,0.05000,1.775
+49,mlp.gate_proj,0.0004289962,0.05000,1.136
+49,mlp.up_proj,0.0004409457,0.05000,1.132
+49,mlp.down_proj,0.0002485424,0.05000,7.970
+50,self_attn.k_proj,0.0000364574,0.05000,1.051
+50,self_attn.v_proj,0.0000476124,0.05000,1.045
+50,self_attn.q_proj,0.0002595472,0.05000,1.078
+50,self_attn.o_proj,0.0000738570,0.05000,1.797
+50,mlp.gate_proj,0.0005196592,0.05000,1.125
+50,mlp.up_proj,0.0005209628,0.05000,1.130
+50,mlp.down_proj,0.0004004640,0.05000,8.063
+51,self_attn.k_proj,0.0000649455,0.05000,1.057
+51,self_attn.v_proj,0.0000829220,0.05000,1.049
+51,self_attn.q_proj,0.0004398252,0.05000,1.087
+51,self_attn.o_proj,0.0001423696,0.05000,1.797
+51,mlp.gate_proj,0.0006647636,0.05000,1.153
+51,mlp.up_proj,0.0006608297,0.05000,1.152
+51,mlp.down_proj,0.0006123469,0.05000,8.000
+52,self_attn.k_proj,0.0000878023,0.05000,1.052
+52,self_attn.v_proj,0.0001286716,0.05000,1.054
+52,self_attn.q_proj,0.0006764697,0.05000,1.099
+52,self_attn.o_proj,0.0001523513,0.05000,1.782
+52,mlp.gate_proj,0.0008464120,0.05000,1.124
+52,mlp.up_proj,0.0008526947,0.05000,1.126
+52,mlp.down_proj,0.0008183107,0.05000,8.027
+53,self_attn.k_proj,0.0001403411,0.05000,1.042
+53,self_attn.v_proj,0.0001782136,0.05000,1.037
+53,self_attn.q_proj,0.0009704368,0.05000,1.250
+53,self_attn.o_proj,0.0001480780,0.05000,1.917
+53,mlp.gate_proj,0.0009788685,0.05000,1.131
+53,mlp.up_proj,0.0009995223,0.05000,1.134
+53,mlp.down_proj,0.0012458582,0.05000,8.069
+54,self_attn.k_proj,0.0002222697,0.05000,1.056
+54,self_attn.v_proj,0.0003150965,0.05000,1.046
+54,self_attn.q_proj,0.0015428386,0.05000,1.074
+54,self_attn.o_proj,0.0002995660,0.05000,1.815
+54,mlp.gate_proj,0.0013180814,0.05000,1.135
+54,mlp.up_proj,0.0013410654,0.05000,1.134
+54,mlp.down_proj,0.0016283727,0.05000,7.964
+55,self_attn.k_proj,0.0002455719,0.05000,1.062
+55,self_attn.v_proj,0.0002898146,0.05000,1.053
+55,self_attn.q_proj,0.0016511303,0.05000,1.080
+55,self_attn.o_proj,0.0002813179,0.05000,1.794
+55,mlp.gate_proj,0.0014898408,0.05000,1.446
+55,mlp.up_proj,0.0015437358,0.05000,1.134
+55,mlp.down_proj,0.0021947372,0.05000,8.029
+56,self_attn.k_proj,0.0004278187,0.05000,1.041
+56,self_attn.v_proj,0.0006316985,0.05000,1.039
+56,self_attn.q_proj,0.0029827804,0.05000,1.061
+56,self_attn.o_proj,0.0003085413,0.05000,1.788
+56,mlp.gate_proj,0.0017243970,0.05000,1.164
+56,mlp.up_proj,0.0018149042,0.05000,1.149
+56,mlp.down_proj,0.0027739530,0.05000,8.076
+57,self_attn.k_proj,0.0005359473,0.05000,1.052
+57,self_attn.v_proj,0.0008049904,0.05000,1.044
+57,self_attn.q_proj,0.0038959943,0.05000,1.090
+57,self_attn.o_proj,0.0003918819,0.05000,1.765
+57,mlp.gate_proj,0.0018884934,0.05000,1.139
+57,mlp.up_proj,0.0020396879,0.05000,1.125
+57,mlp.down_proj,0.0037069661,0.05000,7.999
+58,self_attn.k_proj,0.0008708814,0.05000,1.038
+58,self_attn.v_proj,0.0013238839,0.05000,1.060
+58,self_attn.q_proj,0.0062347704,0.05000,1.074
+58,self_attn.o_proj,0.0004224728,0.05000,1.770
+58,mlp.gate_proj,0.0021498542,0.05000,1.140
+58,mlp.up_proj,0.0023638556,0.05000,1.122
+58,mlp.down_proj,0.0048660359,0.05000,8.354
+59,self_attn.k_proj,0.0010695715,0.05000,1.045
+59,self_attn.v_proj,0.0017025579,0.05000,1.064
+59,self_attn.q_proj,0.0078237816,0.05000,1.083
+59,self_attn.o_proj,0.0004261862,0.05000,1.775
+59,mlp.gate_proj,0.0023862109,0.05000,1.255
+59,mlp.up_proj,0.0026503182,0.05000,1.144
+59,mlp.down_proj,0.0074393693,0.05000,8.122
+60,self_attn.k_proj,0.0011864857,0.05000,1.072
+60,self_attn.v_proj,0.0017836547,0.05000,1.071
+60,self_attn.q_proj,0.0079164522,0.05000,1.096
+60,self_attn.o_proj,0.0012012388,0.05000,1.808
+60,mlp.gate_proj,0.0025860246,0.05000,1.145
+60,mlp.up_proj,0.0029487530,0.05000,1.143
+60,mlp.down_proj,0.0112182335,0.05000,8.058
+61,self_attn.k_proj,0.0015718682,0.05000,1.049
+61,self_attn.v_proj,0.0026914134,0.05000,1.048
+61,self_attn.q_proj,0.0114342334,0.05000,1.076
+61,self_attn.o_proj,0.0012516713,0.05000,1.786
+61,mlp.gate_proj,0.0027420398,0.05000,1.126
+61,mlp.up_proj,0.0031601495,0.05000,1.142
+61,mlp.down_proj,0.0159969039,0.05000,7.986
+62,self_attn.k_proj,0.0016475655,0.05000,1.066
+62,self_attn.v_proj,0.0028598230,0.05000,1.049
+62,self_attn.q_proj,0.0114434291,0.05000,1.073
+62,self_attn.o_proj,0.0022906732,0.05000,1.797
+62,mlp.gate_proj,0.0033809583,0.05000,1.133
+62,mlp.up_proj,0.0037481985,0.05000,1.126
+62,mlp.down_proj,0.0255297494,0.05000,8.035
+63,self_attn.k_proj,0.0007640351,0.05000,1.059
+63,self_attn.v_proj,0.0011615969,0.05000,1.046
+63,self_attn.q_proj,0.0052693927,0.05000,1.076
+63,self_attn.o_proj,0.0020771761,0.05000,1.768
+63,mlp.gate_proj,0.0041764780,0.05000,1.125
+63,mlp.up_proj,0.0045288563,0.05000,1.131
+63,mlp.down_proj,0.0907532932,0.05000,8.077

quantize_config.json

@@ -0,0 +1,24 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": false,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:4.2.5"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.05,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "v2": false,
+    "v2_alpha": 0.25,
+    "act_group_aware": false
+  }
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "_commit_hash": null
+}