vanilj/
llama-3-14b-instruct-v1:Q8_0

121 1 year ago

Self-merge Llama 3 14B Instruct

1 year ago

50e2f10ad93e · 15GB ·

model
llama
·
14.1B
·
Q8_0
params
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>",
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

Readme

The GGUF of the self-merged model RDson/Llama-3-14B-Instruct-v1.