Qwen
/

Qwen2.5-VL-72B-Instruct

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (1)

Inference problems for all Qwen2.5 VL models in transformers above 4.49.0

#26 opened 4 days ago by

Ask about the M-RoPE

#25 opened 7 days ago by

Fix typo

#24 opened 9 days ago by

Upload IMG-20250318-WA0007.jpg

#23 opened 11 days ago by

'Qwen2_5_VLProcessor' object has no attribute 'eos_token'

#22 opened 11 days ago by

本地部署72b时，模型输出为空，怎么解决？

#21 opened 16 days ago by

Qwen/Qwen2.5-VL-72B-Instruct

#20 opened 16 days ago by

GGUF

#19 opened 23 days ago by

Could you please share the detailed parameters setting for the online demo?

#18 opened 24 days ago by

vllm推理32k-128k输入

#17 opened 27 days ago by

official finetune example?

#16 opened about 1 month ago by

Anyone pls let me know what hardware can run 72B ?

#15 opened about 1 month ago by

Fix model tree (remove loop)

#14 opened about 1 month ago by

batch inference error

#13 opened about 1 month ago by

Error in preprocessing prompt inputs

#12 opened about 1 month ago by

cannot import name 'Qwen2_5_VLImageProcessor' (on vLLM)

#11 opened about 1 month ago by

Update preprocessor_config.json

#10 opened about 2 months ago by

Hardware Requirements

#9 opened about 2 months ago by

Vision tokens missing from chat template

#8 opened about 2 months ago by

ERROR:hf-to-gguf:Model Qwen2_5_VLForConditionalGeneration is not supported

#7 opened about 2 months ago by

docs(readme): fix typo in README.md

#6 opened about 2 months ago by

Out of Memory on two H100 (80GB) each and load_in_8_bit = True

#4 opened 2 months ago by

Model Memory Requirements

#3 opened 2 months ago by

Video Inference - TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs'

#2 opened 2 months ago by

Qwen/Qwen2.5-VL-72B-Instruct-AWQ and Qwen/Qwen2.5-VL-40<B-Instruct-AWQ please

#1 opened 2 months ago by