Upload folder using huggingface_hub

README.md

@@ -1,13 +1,43 @@
 ---
 library_name: transformers
-license: apache-2.0
-license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE
+license: apache-2.0		
+license_link: https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE
 pipeline_tag: text-generation
+tags:
+- Qwen3
+- GPTQ
+- Int4
+- 量化修复
+- vLLM
 base_model:
-- Qwen/Qwen3-32B
+  - Qwen/Qwen3-32B
+base_model_relation: quantized
 ---
+# Qwen3-32B-GPTQ-Int4
+Base model: [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)
 
-# Qwen3-8B
+<i>This model is quantized to 4-bit with a group size of 128.</i>
+<br>
+<i>Compared to earlier quantized versions, the new quantized model demonstrates better tokens/s efficiency. This improvement comes from setting desc_act=False in the quantization configuration.</i>
+
+```
+vllm serve JunHowie/Qwen3-32B-GPTQ-Int4 
+```
+
+### 【Dependencies】
+```
+vllm>=0.9.2
+```
+
+### 【Model Download】
+
+```python
+from huggingface_hub import snapshot_download
+snapshot_download('JunHowie/Qwen3-32B-GPTQ-Int4', cache_dir="your_local_path")
+```
+
+### 【Overview】
+# Qwen3-32B
 <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
     <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
 </a>
@@ -24,13 +54,13 @@ Qwen3 is the latest generation of large language models in Qwen series, offering
 
 ## Model Overview
 
-**Qwen3-8B** has the following features:
+**Qwen3-32B** has the following features:
 - Type: Causal Language Models
 - Training Stage: Pretraining & Post-training
-- Number of Parameters: 8.2B
-- Number of Paramaters (Non-Embedding): 6.95B
-- Number of Layers: 36
-- Number of Attention Heads (GQA): 32 for Q and 8 for KV
+- Number of Parameters: 32.8B
+- Number of Paramaters (Non-Embedding): 31.2B
+- Number of Layers: 64
+- Number of Attention Heads (GQA): 64 for Q and 8 for KV
 - Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts). 
 
 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
@@ -48,7 +78,7 @@ The following contains a code snippet illustrating how to use the model generate
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "Qwen/Qwen3-8B"
+model_name = "Qwen/Qwen3-32B"
 
 # load the tokenizer and the model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -95,11 +125,11 @@ print("content:", content)
 For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
 - SGLang:
     ```shell
-    python -m sglang.launch_server --model-path Qwen/Qwen3-8B --reasoning-parser qwen3
+    python -m sglang.launch_server --model-path Qwen/Qwen3-32B --reasoning-parser qwen3
     ```
 - vLLM:
     ```shell
-    vllm serve Qwen/Qwen3-8B --enable-reasoning --reasoning-parser deepseek_r1
+    vllm serve Qwen/Qwen3-32B --enable-reasoning --reasoning-parser deepseek_r1
     ```
 
 For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
@@ -157,7 +187,7 @@ Here is an example of a multi-turn conversation:
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 class QwenChatbot:
-    def __init__(self, model_name="Qwen/Qwen3-8B"):
+    def __init__(self, model_name="Qwen/Qwen3-32B"):
         self.tokenizer = AutoTokenizer.from_pretrained(model_name)
         self.model = AutoModelForCausalLM.from_pretrained(model_name)
         self.history = []
@@ -220,7 +250,7 @@ from qwen_agent.agents import Assistant
 
 # Define LLM
 llm_cfg = {
-    'model': 'Qwen3-8B',
+    'model': 'Qwen3-32B',
 
     # Use the endpoint provided by Alibaba Model Studio:
     # 'model_type': 'qwen_dashscope',
@@ -341,11 +371,13 @@ To achieve optimal performance, we recommend the following settings:
 If you find our work helpful, feel free to give us a cite.
 
 ```
-@misc{qwen3,
-    title  = {Qwen3},
-    url    = {https://qwenlm.github.io/blog/qwen3/},
-    author = {Qwen Team},
-    month  = {April},
-    year   = {2025}
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
 }
 ```

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -11,6 +11,72 @@
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 25600,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 40960,
   "max_window_layers": 64,
   "model_type": "qwen3",
@@ -20,19 +86,22 @@
   "quantization_config": {
     "bits": 4,
     "checkpoint_format": "gptq",
-    "desc_act": true,
+    "desc_act": false,
     "group_size": 128,
+    "hyb_act": false,
     "lm_head": false,
     "meta": {
-      "damp_auto_increment": 0.0025,
-      "damp_percent": 0.01,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.05,
       "mse": 0.0,
       "quantizer": [
-        "gptqmodel:2.2.0"
+        "gptqmodel:4.0.0"
       ],
       "static_groups": false,
       "true_sequential": true,
-      "uri": "https://github.com/modelcloud/gptqmodel"
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "v2": false,
+      "v2_alpha": 0.25
     },
     "pack_dtype": "int32",
     "quant_method": "gptq",
@@ -44,7 +113,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.55.4",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.55.4"
 }

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc6ec84831edaaa8d9bcecc855d3f3569f1caf07404e8c80b04d39517a5d76e
+oid sha256:c75484e00c53c856cf13e83f3044e1571865aaca18d43838567ac77d1a4361f9
 size 3955280848

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0885d8eb4de48779f3b518012610b46328640fa635c6119038efb8b72be3ace5
+oid sha256:65b9a0c401e2fd56c25fc004e22b0484f1ab7fa490945a421dbc3819e85f4bce
 size 3989151776

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f93a39345fb6c00596be11b52927fef74ebd2e0938ed22a3d3a077d8176173b
+oid sha256:5a98fc0af450a79bbdfa87eb26260c00fa6e85fa6e720d04793e1cdd32943fdf
 size 3939923288

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9999b34cb29c778301f95cd381939f933c9947ae46501b4d80240c7c325be8de
+oid sha256:e4906973e652827fe1fdb5d235ae841167bd6b64be76d57dc2350052a8bb766d
 size 3989151824

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7717e6e58502cd1201917a54886e7a56ca8b005d0ef11110bcb0f5c4428fa7
+oid sha256:8ef93fd755b78d6ab1be4f196a1434e9042f42078a4cf482da8c8c6225e030fd
 size 3467226552

quantize_config.json

@@ -1,7 +1,8 @@
 {
   "bits": 4,
   "group_size": 128,
-  "desc_act": true,
+  "desc_act": false,
+  "hyb_act": false,
   "sym": true,
   "lm_head": false,
   "quant_method": "gptq",
@@ -9,13 +10,15 @@
   "pack_dtype": "int32",
   "meta": {
     "quantizer": [
-      "gptqmodel:2.2.0"
+      "gptqmodel:4.0.0"
     ],
     "uri": "https://github.com/modelcloud/gptqmodel",
-    "damp_percent": 0.01,
-    "damp_auto_increment": 0.0025,
+    "damp_percent": 0.05,
+    "damp_auto_increment": 0.01,
     "static_groups": false,
     "true_sequential": true,
-    "mse": 0.0
+    "mse": 0.0,
+    "v2": false,
+    "v2_alpha": 0.25
   }
 }

tokenizer_config.json

@@ -227,7 +227,6 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",