# MiniGPT-4 建構 這篇論文是照著[MiniGPT-4](https://github.com/Vision-CAIR/MiniGPT-4)的指示建立的, --- 首先到了2. Prepare the pretrained Vicuna weights這步會有重大問題,就是需要的權重需要用私下的手段取得。我這邊的權重來自[shawwn](https://github.com/shawwn/llama-dl)。用shawwn的方法只能下載到prototype,另外還需用程式轉換 ``` python src/transformers/models/llama/convert_llama_weights_to_hf.py \ --input_dir /path/to/downloaded/llama/weights --model_size 7B --output_dir /output/path ``` 上面指令應該是可以轉成hf檔放到llama-13bOR7b-hf資料夾,然後再照[PrepareVicna](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/PrepareVicuna.md)建好vicuna。 以上應該就差不多好了。
×
Sign in
Email
Password
Forgot password
or
By clicking below, you agree to our
terms of service
.
Sign in via Facebook
Sign in via Twitter
Sign in via GitHub
Sign in via Dropbox
Sign in with Wallet
Wallet (
)
Connect another wallet
New to HackMD?
Sign up