Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne
274 Pulls Updated 5 months ago
Updated 6 months ago
6 months ago
0a8f93ca7b66 · 4.5GB
model
archllama
·
parameters11.5B
·
quantizationQ2_K
4.5GB
Readme
Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne
Quantized with imatrix using groups_merged.txt