Qwen2-VL-72B-Instruct-GPTQ-Int8 / model-00017-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 about 1 year ago

3.93 GB

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

( Raw pointer file )

SHA256:: a3257b539618933c2dbaa57d0b133815bd167415fedf06f0ce76f7aebc3b9bd9
Pointer size:: 135 Bytes
Size of remote file:: 3.93 GB
Xet backed hash:: d3e92c8ef6db532bca860a1f4077a100ab42aa7b1136b2fb7009542d254aa590

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