Qwen2-VL-72B-Instruct-GPTQ-Int8 / model-00012-of-00021.safetensors

可亲

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

d1eab90 11 months ago

3.86 GB

This file is stored with Xet . It is too big to display, but you can still download it.

( Raw pointer file )

SHA256:: 7ebcfd57658001265ac2e935bf6c323f2d850fe61d6589abe80a5a327733befe
Pointer size:: 135 Bytes
Size of remote file:: 3.86 GB
Xet backed hash:: 6e76de2f48f1ff5b03fce3b78484801c9b7e036748b70dc97915242977603b37

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.