OpenGVLab / Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
https://vchat.opengvlab.com/
MIT License
2.86k stars 230 forks source link

Missing files #58

Closed adeobootpin closed 10 months ago

adeobootpin commented 11 months ago

Hello,

When I run the following command: python apply_delta.py --base ./llama-13b --target stable-vicuna-13b --delta pvduy/stable-vicuna-13b-delta

I get this error: OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory ./llama-13b.

Where do I find the missing files? Or did I miss something in a previous step?

Thanks

karrymao commented 11 months ago

You may run

python apply_delta.py \
  --base decapoda-research/llama-13b-hf \
  --target stable-vicuna-13b \
  --delta CarperAI/stable-vicuna-13b-delta

It will automatically download (and cache) llama weights from huggingface.