Qwen2-VL-2B-4bit / README.md
prince-canuma's picture
Upload folder using huggingface_hub
5f534f0 verified
|
raw
history blame contribute delete
No virus
529 Bytes
metadata
language:
  - en
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
  - multimodal
  - mlx

mlx-community/Qwen2-VL-2B-4bit

This model was converted to MLX format from Qwen/Qwen2-VL-2B using mlx-vlm version 0.0.13. 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/Qwen2-VL-2B-4bit --max-tokens 100 --temp 0.0