Qwen
/

Qwen2.5-VL-72B-Instruct-AWQ

Image-Text-to-Text

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Resources

View closed (1)

ImportError: cannot import name 'shard_checkpoint' from 'transformers.modeling_utils

#12 opened 3 days ago by

Change the image_processor_type

#11 opened 4 days ago by

如何提高推理速率

#10 opened 5 days ago by

kevinBusinessGenrator

我们现在使用的图片token数量远没有达到32768个，如何能够降低这个数量

#9 opened 5 days ago by

kevinBusinessGenrator

VLLM部署报错

#8 opened 12 days ago by

Update preprocessor_config.json

#7 opened 12 days ago by

intermediate_size改动

#6 opened 13 days ago by

is this bug? "image_processor_type": "Qwen2_5_VLImageProcessor",

#5 opened 13 days ago by

How to speed up inference?

#4 opened 15 days ago by

vegasscientific

Add link to paper in model card

#3 opened 17 days ago by

AWQ量化版损失有多大？可以再进行SFT微调吗？

#1 opened 18 days ago by