reflection

A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

70B

49.3K Pulls Updated 10 days ago

template

6a340fffade7 · 297B

{{- range $i, $_ := .Messages }}<|start_header_id|>{{ .Role }}<|end_header_id|> {{ .Content }} {{- if ne (len (slice $.Messages $i)) 1 }}<|eot_id|> {{- else if ne .Role "assistant" }}<|eot_id|> {{- if eq .Role "user" }} <|start_header_id|>assistant<|end_header_id|> {{- end }} {{- end }} {{ end }}