Qwen
/

Qwen2-VL-72B-Instruct-AWQ

Image-Text-to-Text

4-bit precision

Model card Files Files and versions Community

Qwen2-VL-72B-Instruct-AWQ / model-00003-of-00011.safetensors

Commit History

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm

688e28d

可亲 commited on Sep 24

Upload folder using huggingface_hub

3eb1d44
verified

clonefy commited on Sep 17