The first open-source successful RL attempt on already long-COT finetuned models of simialr sizes under light budget. Light-R1-14B is also the State-Of-The-Art 14B math model with AIME24 & 25 scores 74.0 & 60.2, outperforming many 32B models.
7b
14b
32b
2,562 Pulls Updated 2 weeks ago
686278c0ae95 · 395B
"{{- if .System }}{{ .System }}{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1}}
{{- if eq .Role "user" }}<｜User｜>{{ .Content }}
{{- else if eq .Role "assistant" }}<｜Assistant｜>{{ .Content }}{{- if not $last }}<｜end▁of▁sentence｜>{{- end }}
{{- end }}
{{- if and $last (ne .Role "assistant") }}<｜Assistant｜>{{- end }}
{{- end }}