wenge-research commited on
Commit
cf32f97
1 Parent(s): 4f301cb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -9
README.md CHANGED
@@ -6,7 +6,7 @@ license: other
6
  <h1>
7
  YAYI 2
8
  </h1>
9
- <br>
10
  </div>
11
 
12
  <div align="center">
@@ -38,16 +38,17 @@ For more details about the YAYI 2, please refer to our GitHub repository. Stay t
38
  | sequence length | 4096 |
39
 
40
 
 
41
 
42
- ## 要求 Requirements)
 
 
 
43
 
44
- python 3.8及以上版本
45
- pytorch 1.12及以上版本,推荐2.0及以上版本
46
- 建议使用CUDA 11.4及以上(GPU用户、flash-attention用户等需考虑此选项)
47
- 运行BF16或FP16模型需要多卡至少144GB显存(例如2xA100-80G或5xV100-32G);运行Int4模型至少需要48GB显存(例如1xA100-80G或2xV100-32G)。
48
- python 3.8 and above
49
- pytorch 1.12 and above, 2.0 and above are recommended
50
- CUDA 11.4 and above are recommended (this is for GPU users, flash-attention users, etc.) To run Qwen-72B-Chat in bf16/fp16, at least 144GB GPU memory is required (e.g., 2xA100-80G or 5xV100-32G). To run it in int4, at least 48GB GPU memory is requred (e.g., 1xA100-80G or 2xV100-32G).
51
 
52
 
53
  ## 快速开始/Quick Start
 
6
  <h1>
7
  YAYI 2
8
  </h1>
9
+ <!-- <br> -->
10
  </div>
11
 
12
  <div align="center">
 
38
  | sequence length | 4096 |
39
 
40
 
41
+ ## 要求/Requirements
42
 
43
+ * python 3.8及以上版本
44
+ * pytorch 2.0.1 及以上版本
45
+ * 建议使用 CUDA 11.7 及以上
46
+ * 运行 BF16 或 FP16 模型需要至少80GB显存(例如1xA100)
47
 
48
+ * python 3.8 and above
49
+ * pytorch 2.0.1 and above
50
+ * CUDA 11.7 and above are recommended
51
+ * To run YAYI-30B in bf16/fp16, at least 80B GPU memory is required (e.g., 1xA100-80G)
 
 
 
52
 
53
 
54
  ## 快速开始/Quick Start