44 lines
1.3 KiB
YAML
44 lines
1.3 KiB
YAML
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
|