nm-testing
/

Mixtral-8x7B-Instruct-v0.1-W8A8-quantized

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-W8A8-quantized / generation_config.json

Commit History

Upload folder using huggingface_hub

9f5c3d2
verified

sadkins65 commited on Aug 8, 2024