RYDE-WORK/MiniCPM
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/MiniCPM.git synced 2026-02-03 13:49:30 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
DingDing 2024-02-02 17:36:05 +08:00 committed by GitHub
parent 1994166f0a
commit 3e868cd671
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -109,7 +109,7 @@ python inference.py --model_path <vllmcpm_repo_path> --prompt_path prompts/promp
``` ```
#### Huggingface 模型 #### Huggingface 模型
（注：我们发现当前Huggingface的推理代码推理效果差于Vllm的推理代码，我们正在对齐中，目前已定为到PageAttention和普通attention的区别，请耐心等待） （注：我们发现当前Huggingface的推理代码推理效果差于Vllm的推理代码，我们正在对齐中，目前已定位到attention计算的精度问题，请耐心等待）
##### MiniCPM-2B ##### MiniCPM-2B
* 安装`transformers>=4.36.0`以及`accelerate`后，运行以下代码 * 安装`transformers>=4.36.0`以及`accelerate`后，运行以下代码
```python ```python