lucas2024 / mistral-nemo-minitron-8b-instruct

model

archllama

·

parameters8.41B

·

quantizationQ8_0

8.9GB

params

{"stop":["<extra_id_0>","<extra_id_1>"]}

61B

template

{{ if .System }}<extra_id_0>System {{ .System }} {{ end }} {{ if .Prompt }}<extra_id_1>User {{ .Prompt }} <extra_id_1>Assistant {{ .Response }}{{ end }}

153B