JunHowie commited on
Commit
463f2c0
·
verified ·
1 Parent(s): 5e33e46

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -11
README.md CHANGED
@@ -12,15 +12,15 @@ base_model:
12
  base_model_relation: quantized
13
  ---
14
  # Qwen3-Coder-30B-A3B-Instruct-AWQ
15
- 基础型 [Qwen3-Coder-30B-A3B-Instruct](https://www.modelscope.cn/models/Qwen3-Coder-30B-A3B-Instruct)
16
 
17
 
18
- ### 【❗❗提醒❗❗】
19
- 该模型4比特量化损失较大,需谨慎使用
20
 
21
 
22
- ### 【Vllm 启动命令】
23
- <i>注: 4卡启动该模型一定要跟`--enable-expert-parallel` ,否则其专家张量TP整除除不尽;2卡则不需要。 </i>
24
  ```
25
  CONTEXT_LENGTH=32768
26
 
@@ -40,33 +40,35 @@ vllm serve \
40
  --port 8000
41
  ```
42
 
43
- ### 【依赖】
44
 
45
  ```
46
  vllm==0.10.0
47
  ```
48
 
49
- ### 【模型更新日期】
50
- ```
 
 
51
  2025-08-01
52
  1. 首次commit
53
  ```
54
 
55
- ### 【模型列表】
56
 
57
  | 文件大小 | 最近更新时间 |
58
  |--------|--------------|
59
  | `16GB` | `2025-08-01` |
60
 
61
 
62
- ### 【模型下载】
63
 
64
  ```python
65
  from modelscope import snapshot_download
66
  snapshot_download('tclf90/Qwen3-Coder-30B-A3B-Instruct-AWQ', cache_dir="本地路径")
67
  ```
68
 
69
- ### 【介绍】
70
  # Qwen3-Coder-30B-A3B-Instruct
71
  <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
72
  <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;"/>
 
12
  base_model_relation: quantized
13
  ---
14
  # Qwen3-Coder-30B-A3B-Instruct-AWQ
15
+ Base model [Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct)
16
 
17
 
18
+ ### ❗❗Reminder❗❗
19
+ This model suffers from significant loss under 4-bit quantization, please use with caution.
20
 
21
 
22
+ ### 【vLLM Single Node with 4 GPUs Startup Command】
23
+ <i>Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs.</i>
24
  ```
25
  CONTEXT_LENGTH=32768
26
 
 
40
  --port 8000
41
  ```
42
 
43
+ ### 【Dependencies】
44
 
45
  ```
46
  vllm==0.10.0
47
  ```
48
 
49
+ ### 【Model Update Date】
50
+ ```
51
+ 2025-08-19
52
+ 1.[BugFix] Fix compatibility issues with vLLM 0.10.1
53
  2025-08-01
54
  1. 首次commit
55
  ```
56
 
57
+ ### 【Model Files】
58
 
59
  | 文件大小 | 最近更新时间 |
60
  |--------|--------------|
61
  | `16GB` | `2025-08-01` |
62
 
63
 
64
+ ### 【Model Download】
65
 
66
  ```python
67
  from modelscope import snapshot_download
68
  snapshot_download('tclf90/Qwen3-Coder-30B-A3B-Instruct-AWQ', cache_dir="本地路径")
69
  ```
70
 
71
+ ### 【Overview】
72
  # Qwen3-Coder-30B-A3B-Instruct
73
  <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
74
  <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;"/>