Today
-
Save plain SFT/RL web-heavy__16m__reward_modeling
-
Save plain SFT/RL baseline__16m__reward_modeling
-
Save plain SFT/RL math-heavy__8m__reward_modeling
-
Save plain SFT/RL code-heavy__64m__reward_modeling
-
Save plain SFT/RL code-heavy__32m__reward_modeling
-
Save plain SFT/RL code-heavy__64m__reward_modeling
-
Save plain SFT/RL code-heavy__16m__reward_modeling
-
Save plain SFT/RL code-heavy__32m__reward_modeling
-
Save plain SFT/RL chat-heavy__64m__reward_modeling
-
Save plain SFT/RL code-heavy__16m__reward_modeling
-
Save plain SFT/RL code-heavy__8m__reward_modeling
-
Save plain SFT/RL code-heavy__8m__reward_modeling
-
Save plain SFT/RL web-heavy__32m__reward_modeling
-
Save plain SFT/RL chat-heavy__16m__reward_modeling
-
Save plain SFT/RL chat-heavy__8m__reward_modeling
-
Save plain SFT/RL math-heavy__64m__reward_modeling
-
Save plain SFT/RL baseline__64m__reward_modeling
-
Save plain SFT/RL math-heavy__32m__reward_modeling
-
Save plain SFT/RL math-heavy__16m__reward_modeling
-
Save plain SFT/RL baseline__32m__reward_modeling
-
Save plain SFT/RL web-heavy__8m__reward_modeling
-
Save plain SFT/RL web-heavy__16m__reward_modeling
-
Save plain SFT/RL baseline__16m__reward_modeling
-
Save plain SFT/RL baseline__8m__reward_modeling
-
initial commit