starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-20 16:35:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README_JA.md

Browse Source
This commit is contained in:
Yang An
2023-08-22 08:42:13 +08:00
committed by GitHub
parent a998547409
commit ce5f0e18c6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README_JA.md
View File

@@ -254,7 +254,7 @@ BF16の精度とInt4の量子化レベルの下で、それぞれ2048個と8192
| Quantization Level | Peak Usage for Encoding 2048 Tokens | Peak Usage for Generating 8192 Tokens | | Quantization Level | Peak Usage for Encoding 2048 Tokens | Peak Usage for Generating 8192 Tokens |
| ------------------ | :---------------------------------: | :-----------------------------------: | | ------------------ | :---------------------------------: | :-----------------------------------: |
| BF16 | 18.99GB | 24.40GB | | BF16 | 18.99GB | 24.40GB |
| In4 | 10.20GB | 15.61GB | | Int4 | 10.20GB | 15.61GB |
上記のスピードとメモリーのプロファイリングは、[このスクリプト](https://qianwen-res.oss-cn-beijing.aliyuncs.com/profile.py)を使用しています。 上記のスピードとメモリーのプロファイリングは、[このスクリプト](https://qianwen-res.oss-cn-beijing.aliyuncs.com/profile.py)を使用しています。