Active filters: nickhe
nickhe/sft-ALL-checkpoint-2000
8B • Updated • 4
nickhe/sft-shooting_sports_maze_action-checkpoint-3000
8B • Updated • 4
8B • Updated • 5
nickhe/sft-adventure-ckpt-3750
8B • Updated • 3
8B • Updated • 3
nickhe/sft-maze-ckpt-2000
8B • Updated • 3
8B • Updated • 3
nickhe/rl-sports-ckpt-300
8B • Updated • 3
nickhe/atari_sft_adventure_14_AUG-ckpt-2000
8B • Updated • 3
nickhe/rl-lora-env-reward-ckpt-400
Updated
nickhe/rl_env_shooting4f_lora_0827-ckpt-200
Updated
nickhe/rl_env_all_all_games_lora_0827-ckpt-400
Updated
nickhe/rl_env_all_all_games_lora_0827-ckpt-600
Updated
nickhe/rl_env_shooting4f_lora_0827-ckpt-400
Updated
nickhe/atari_sft_maze-ckpt-2500
8B • Updated • 3
nickhe/dr-verl-0915-step600
8B • Updated • 3
nickhe/dr-verl-0915-step300
8B • Updated • 3
nickhe/ga_rl_sports_15_AUG
Updated
nickhe/rl_env_all_lora_0827
Updated
nickhe/rl_dqn_all_lora_kl_0915_step_1200
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_800
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1000
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1400
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1600
Updated
nickhe/dr_verl_4gpu_0920_math7b_step_300
8B • Updated • 5
nickhe/dr_verl_4gpu_0920_math7b_step_600
Updated
nickhe/dr_verl_4gpu_0920_math7b_step_900
8B • Updated • 4
nickhe/dr_verl_4gpu_0920_math7b_step_1200
8B • Updated • 5
nickhe/rl_dqn_all_lora_kl_0915-step_1600
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_1800
Updated