FunAGI
/

Qwen2.5-Omni-7B-GPTQ-4bit

4-bit precision

Model card Files Files and versions

Resources

View closed (0)

Delete tokenizer_config.json

#6 opened 5 months ago by

Delete tokenizer_config.json

#5 opened 5 months ago by

Delete tokenizer_config.json

#4 opened 5 months ago by

vllm error

#3 opened 6 months ago by

Can you create an 8bit version?

#2 opened 7 months ago by

test the inference script and quantized model, but have error as below

#1 opened 7 months ago by