deepseek-v3:671b

2M 7 months ago

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b
... /
template
c5ce92dfece1 · 359B
{{- range $i, $_ := .Messages }}
{{- if eq .Role "user" }}<｜User｜>
{{- else if eq .Role "assistant" }}<｜Assistant｜>
{{- end }}{{ .Content }}
{{- if eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<｜Assistant｜>
{{- end }}
{{- else if eq .Role "assistant" }}<｜end▁of▁sentence｜><｜begin▁of▁sentence｜>
{{- end }}
{{- end }}