metadata
license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
tags:
- multimodal
- mlx
library_name: transformers
base_model:
- Qwen/Qwen2-VL-2B
EZCon/Qwen2-VL-2B-Instruct-8bit-mlx
This model was converted to MLX format from Qwen/Qwen2-VL-2B-Instruct using mlx-vlm version 0.3.2.
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 EZCon/Qwen2-VL-2B-Instruct-8bit-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>