Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Qwen
/
Qwen2.5-VL-32B-Instruct-AWQ

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-to-text
multimodal
conversational
text-generation-inference
4-bit precision
awq
Model card Files Files and versions
xet
Community
13
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

some weights not initialized problem with transformers library.

πŸ‘ πŸ‘€ 7
4
#13 opened 3 months ago by
robotrule

Update README.md

#12 opened 3 months ago by
megladagon

(vLLM) Tool calling broken after update to tokenizer_config.json

#10 opened 3 months ago by
m1das13

RuntimeError: expected mat1 and mat2 to have the same dtype, but got: struct c10::Half != struct c10::BFloat16

5
#9 opened 4 months ago by
rameshch

AssertionError: Both operands must be same dtype. Got fp16 and bf16

18
#8 opened 4 months ago by
treehugg3

can it work on single 3090?

1
#7 opened 4 months ago by
hamaadtahiir

Model does not produce meaningful output for VQA

πŸ‘€ 1
1
#6 opened 4 months ago by
rpeinl

The inference speed of the AWQ model is slower than that of the original model

#4 opened 4 months ago by
wakakakakawa

Quality issues with AWQ Model

4
#3 opened 4 months ago by
bggmyfuture-ai

Should have a `image_processor_type` key

πŸ‘ 3
1
#2 opened 4 months ago by
Gierry

Unrecognized image processor in Qwen/Qwen2.5-VL-32B-Instruct-AWQ.

πŸ‘ 1
2
#1 opened 4 months ago by
acidz1
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs