numen-tech
/

Llama-3-8B-Instruct-MopeyMule-w3a16g40sym

Model card Files Files and versions

Llama-3-8B-Instruct-MopeyMule-w3a16g40sym / README.md

numen-tech's picture

Add weights

1b10dd1 over 1 year ago

|

history blame contribute delete

198 Bytes

metadata

license: llama3

3-bit OmniQuant quantized version of Llama-3-8B-Instruct-MopeyMule.