OpenGVLab

/

InternVL2-40B

like 89

SWIFT from ModelScope community has supported the fine-tuning(Image/Video) of InternVL2, please check:
https://github.com/modelscope/swift/blob/main/docs/source_en/Multi-Modal/internvl-best-practice.md
or use:

# install 
pip install git+https://github.com/modelscope/swift.git
# run
CUDA_VISIBLE_DEVICES=0 swift sft \
    --model_type internvl2-40b \
    --dataset video-chatgpt