Visual Question Answering
Transformers
Safetensors
MLX
English
qwen2_5_vl
image-text-to-text
multimodal
text-generation-inference
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("mlx-community/VL-Rethinker-72B-4bit")
model = AutoModelForMultimodalLM.from_pretrained("mlx-community/VL-Rethinker-72B-4bit", device_map="auto")Quick Links
mlx-community/VL-Rethinker-72B-4bit
This model was converted to MLX format from TIGER-Lab/VL-Rethinker-72B using mlx-vlm version 0.1.22.
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/VL-Rethinker-72B-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
- Downloads last month
- 11
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mlx-community/VL-Rethinker-72B-4bit
Base model
Qwen/Qwen2.5-VL-7B-Instruct
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="mlx-community/VL-Rethinker-72B-4bit")