anhbn
/

Phi-3.5-mini-instruct-quantized.w8a8

8-bit precision

compressed-tensors

Model card Files Files and versions

Phi-3.5-mini-instruct-quantized.w8a8

4.42 GB

1 contributor

History: 2 commits

anhbn's picture

Upload folder using huggingface_hub

b281c7c verified about 1 year ago