Qwen
/

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

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions

Resources

View closed (2)

RuntimeError: Cannot load `awq` weight, make sure the model is already quantized

#17 opened 5 months ago by

RuntimeError: probability tensor contains either inf, nan or element < 0

#16 opened 6 months ago by

Update README.md

#15 opened 7 months ago by

sglang的chat-template什么时候能设置v2.5-vl

#14 opened 8 months ago by

kevinBusinessGenrator

修改视觉模型的tokens_per_second没有生效

#13 opened 8 months ago by

kevinBusinessGenrator

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

#12 opened 8 months ago by

Change the image_processor_type

#11 opened 8 months ago by

如何提高推理速率

#10 opened 8 months 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 8 months ago by

kevinBusinessGenrator

VLLM部署报错

#8 opened 8 months ago by

intermediate_size改动

#6 opened 8 months ago by

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

#5 opened 8 months ago by

How to speed up inference?

#4 opened 8 months ago by

vegasscientific

Add link to paper in model card

#3 opened 8 months ago by

AWQ量化版损失有多大？可以再进行SFT微调吗？

#1 opened 8 months ago by