README.md

metadata

license: apache-2.0
datasets:
  - HuggingFaceM4/OBELICS
  - HuggingFaceM4/the_cauldron
  - HuggingFaceM4/Docmatix
  - HuggingFaceM4/WebSight
language:
  - en
tags:
  - multimodal
  - vision
  - image-text-to-text
  - mlx
library_name: transformers

mlx-community/Idefics3-8B-Llama3-4bit

This model was converted to MLX format from HuggingFaceM4/Idefics3-8B-Llama3 using mlx-vlm version 0.1.12. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/Idefics3-8B-Llama3-4bit --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>