Edit model card

This is a copy of 'Qwen/Qwen-VL-Chat-Int4' but with the possibility to pass the image tensors as a parameter, not downloading them from internet. model.forward(**inputs) -> model.forward(**inputs, image_list)

Downloads last month
40
Safetensors
Model size
4.05B params
Tensor type
FP16
·
I32
·
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.