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)
110 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
bf4595197c5a · 40GB
model
archllama
·
parameters70.6B
·
quantizationQ4_K_S
40GB
params
{"num_ctx":8192,"stop":["\u003c|start_header_id|\u003e","\u003c|end_header_id|\u003e","\u003c|end_of
171B
template
"{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .
257B
Readme
No readme