1
0
mirror of https://github.com/Vision-CAIR/MiniGPT-4.git synced 2025-04-09 12:30:45 +00:00

Update README.md

This commit is contained in:
XiaoqianShen 2023-04-20 19:36:57 +03:00 committed by GitHub
parent 6d7965d857
commit 525970b7ea
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -84,6 +84,8 @@ Try out our demo [demo.py](demo.py) on your local machine by running
python demo.py --cfg-path eval_configs/minigpt4_eval.yaml --gpu-id 0
```
Thanks [@camenduru](https://github.com/camenduru), you can also run our code on [Colab](https://colab.research.google.com/github/camenduru/MiniGPT-4-colab/blob/main/minigpt4_colab.ipynb)
Here, we load Vicuna as 8 bit by default to save some GPU memory usage.
Besides, the default beam search width is 1.
Under this setting, the demo cost about 23G GPU memory.