THUDM

/

cogvlm2-video-llama3-chat

like 33

SWIFT from ModelScope community has supported the fine-tuning of Cogvlm2, please check:
https://github.com/modelscope/swift/blob/main/docs/source_en/Multi-Modal/cogvlm2-video-best-practice.md
or use:

# install 
pip install git+https://github.com/modelscope/swift.git
# run
CUDA_VISIBLE_DEVICES=0 swift sft \
    --model_type cogvlm2-video-13b-chat \
    --dataset video-chatgpt