model

archllama

·

parameters70.6B

·

quantizationQ5_K_M

50GB

params

{ "min_p": 0.9, "num_batch": 1024, "num_ctx": 65536, "num_keep": 256, "temperatu

90B

template

{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {

1.5kB