metadata

base_model: llava-hf/llava-1.5-7b-hf
language:
  - en
library_name: transformers
pipeline_tag: image-text-to-text
license: llama2
tags:
  - multimodal
  - llava
  - vision
  - unsloth
  - mlx

shashikanth-a/llava-1.5-7b-hf-4bit

This model was converted to MLX format from unsloth/llava-1.5-7b-hf using mlx-vlm version 0.1.3. 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 shashikanth-a/llava-1.5-7b-hf-4bit --max-tokens 100 --temp 0.0