Collections:
  - Name: Otter
    Metadata:
      Architecture:
        - Transformer
        - Gated Cross-Attention Dense
    Paper:
      Title: 'Otter: A Multi-Modal Model with In-Context Instruction Tuning'
      URL: https://arxiv.org/abs/2305.03726
    README: configs/otter/README.md

Models:
  - Name: otter-9b_3rdparty_caption
    Metadata:
      FLOPs: null
      Parameters: 8220452880
    In Collection: Otter
    Results:
      - Task: Image Caption
        Dataset: COCO
        Metrics:
          BLEU-4: null
          CIDER: null
    Weights: https://download.openmmlab.com/mmclassification/v1/otter/otter-9b-adapter_20230613-51c5be8d.pth
    Config: configs/otter/otter-9b_caption.py
    Converted From:
      Weights: https://huggingface.co/luodian/otter-9b-hf
      Code: https://github.com/Luodian/Otter/tree/main
  - Name: otter-9b_3rdparty_vqa
    Metadata:
      FLOPs: null
      Parameters: 8220452880
    In Collection: Otter
    Results:
      - Task: Visual Question Answering
        Dataset: VQAv2
        Metrics:
          Accuracy: null
    Weights: https://download.openmmlab.com/mmclassification/v1/otter/otter-9b-adapter_20230613-51c5be8d.pth
    Config: configs/otter/otter-9b_vqa.py
    Converted From:
      Weights: https://huggingface.co/luodian/otter-9b-hf
      Code: https://github.com/Luodian/Otter/tree/main