cwchang/
llama-3-taiwan-70b-instruct:q8_0

254 1 year ago

The model used is a quantized version of `Llama-3-Taiwan-70B-Instruct`. More details can be found on the website (https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)

1 year ago

81803f62e25b · 75GB ·

model
llama
·
45.2B
·
Q8_0
model
·
25.4B
·
F32
template
"{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .P
params
{ "num_ctx": 8192, "stop": [ "<|start_header_id|>", "<|end_header_id|>",

Readme

No readme