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

Updated 6 months ago

6 months ago

89040324e2ad · 20GB

archqwen2

parameters32.8B

quantizationQ4_K_M

20GB

"{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slic

395B

{ "stop": [ "<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>",

148B

Readme