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

153 3 months ago

tools

3 months ago

6170b79c1bbe · 4.8GB

model
llama
·
4.51B
·
Q8_0
template
<|start_header_id|>system<|end_header_id|> {{ if .Tools }}You have access to the following functions
system
<|start_header_id|>detailed thinking off<|end_header_id|>
params
{ "num_predict": 1024, "repeat_penalty": 1.15, "stop": [ "<|start_header_id|>",

Readme

No readme