avil/
nvidia-llama-3.1-nemotron-nano-4b-v1.1:thinking-on

226 6 months ago

tools

6 months ago

26282d23cc6b · 4.8GB ·

model
llama
·
4.51B
·
Q8_0
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr
system
<|start_header_id|>detailed thinking on<|end_header_id|>
params
{ "num_ctx": 131072, "num_predict": 4096, "repeat_penalty": 1.1, "temperature": 0.7,

Readme

No readme