86 1 year ago

The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct-DPO`. More details can be found on the website (https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-DPO)

1 year ago

e495357aca5c · 5.6GB ·

llama
·
8.03B
·
Q5_0
"{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .P
{ "num_ctx": 8192, "stop": [ "<|start_header_id|>", "<|end_header_id|>",

Readme

No readme