Visual Question Answering
Transformers
Safetensors
English
videollama2_mistral
text-generation
multimodal large language model
large video-language model

Commit History

  1. fix data form support

    614cc6d
  2. support path input from HF UI

    b80570e
  3. change flash_attention_2 to eager

    142339c
  4. fix: disable flash attention 2 for CLIPVisionModel

    723daaf
  5. Disable Flash Attention for CLIP

    e65359a
  6. Add videollama2 model code

    2e0bbea
  7. add dependencies to requirements.txt

    af262cd

  1. Add custom handler and requirements

    d4a7de9
  2. Duplicate from DAMO-NLP-SG/VideoLLaMA2-7B-16F⁠

    ccclemenfff +1: Zesen Cheng
    9d75944