unsloth
/

Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions

Resources

View closed (2)

vLLM Compatibility Issue with Unsloth's 4-bit Quantized Models - Shape Mismatch During Weight Loading

#9 opened 3 months ago by

Update model type in config.json

#8 opened 3 months ago by

Broken in transformers 4.53 >

#7 opened 4 months ago by

Bnb breaks the function calls

#5 opened 9 months ago by

generation_config.json

#4 opened 9 months ago by

Help getting the example working

#3 opened 9 months ago by

Update preprocessor_config.json

#2 opened 10 months ago by