README.md

metadata

language:
  - en
pipeline_tag: image-text-to-text
tags:
  - vision
  - image-text-to-text
  - mlx

mlx-community/llava-v1.6-34b-8bit

This model was converted to MLX format from llava-hf/llava-v1.6-34b-hf using mlx-vlm version 0.1.0. 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/llava-v1.6-34b-8bit --max-tokens 100 --temp 0.0