Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne
274 Pulls Updated 5 months ago
Updated 5 months ago
5 months ago
327bb229e46c · 3.3GB
model
archllama
·
parameters11.5B
·
quantizationIQ2_XXS
3.3GB
params
{"num_keep":24,"stop":["\u003c|start_header_id|\u003e","\u003c|end_header_id|\u003e","\u003c|eot_id|
110B
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if
260B
Readme
Meta-Llama-3-12B-Instruct is a depth upscaling merge of llama3-8b from M. Labonne
Quantized with imatrix using groups_merged.txt