Idefics3_FT_fr

Idefics3_FT_fr

Idefics3-8B-Llama3 trained with the data in the following collection with this script.

Citation

@misc{laurençon2024building,
      title={Building and better understanding vision-language models: insights and future directions.}, 
      author={Hugo Laurençon and Andrés Marafioti and Victor Sanh and Léo Tronchon},
      year={2024},
      eprint={2408.12637},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}