Model card for FLAME-Mistral-Nemo-ViT-B-16-CC3M

Model description

• Model Type: FLAME-Mistral-Nemo-ViT-B-16 model trained on CC3M.

• Task: Long/short/multilingual-context image-text retrieval, zero-shot image classification.

Uses

See https://github.com/MIV-XJTU/FLAME.

Citation

@article{cao2024flame,
  title={FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training},
  author={Cao, Anjia and Wei, Xing and Ma, Zhiheng},
  journal={arXiv preprint arXiv:2411.11927},
  year={2024}
}