mannix / llama3-12b

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

269 Pulls Updated 3 months ago

4 months ago

dae37e580f01 · 7.3GB

model
llama
·
11.5B
·
Q4_1
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>
params
{"num_keep":24,"stop":["<|start_header_id|>","<|end_header_id|>","<|eot_id|>"]}

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