mannix/
llama3-12b:q2_k

375 1 year ago

Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne

1 year ago

0a8f93ca7b66 · 4.5GB ·

model
llama
·
11.5B
·
Q2_K

Readme

Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne

Quantized with imatrix using groups_merged.txt

https://huggingface.co/mlabonne/Meta-Llama-3-12B-Instruct