README.md

metadata

library_name: transformers
license: apache-2.0
datasets:
  - HuggingFaceM4/the_cauldron
  - HuggingFaceM4/Docmatix
pipeline_tag: image-text-to-text
language:
  - en
base_model:
  - HuggingFaceTB/SmolLM2-135M-Instruct
  - google/siglip-base-patch16-512
tags:
  - mlx

moot20/SmolVLM-256M-Instruct-MLX-4bits

This model was converted to MLX format from HuggingFaceTB/SmolVLM-256M-Instruct 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 moot20/SmolVLM-256M-Instruct-MLX-4bits --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>