Active filters: dureduck
Reinforcement Learning
• Updated • 326
0.5B • Updated • 3
dureduck/1030_dp_model_lift_place_3x4_grid_one_each
Robotics
• 0.3B • Updated • 6
dureduck/1030_dp_model_lift_place_3x4_grid_three_each
Robotics
• 0.3B • Updated • 5
dureduck/1030_dp_lp_nailkit_3x4_grid_3_each
Robotics
• 0.3B • Updated • 7
dureduck/1104_dp_lp_5x4_grid_three_each
Robotics
• 0.3B • Updated • 6
dureduck/1104_dp_lp_9x7_grid_three_each
Robotics
• 0.3B • Updated • 5
dureduck/1104_act_lp_5x4_grid_three_each
Robotics
• 0.3B • Updated • 3
dureduck/1030_act_lp_3x4_grid_three_each
Robotics
• 51.7M • Updated • 4
dureduck/1104_act_lp_9x7_grid_three_each
Robotics
• 51.7M • Updated • 4
dureduck/1106_act_lp_dense_5x4_random_50samples
Robotics
• 51.7M • Updated • 5
dureduck/1109_lp_1loc_5x4_10samples
Robotics
• 51.7M • Updated • 4
dureduck/1109_lp_1loc_5x4_10samples_b16
Robotics
• 51.7M • Updated • 4
dureduck/1109_lp_1loc_5x4_10samples_b32
Robotics
• 51.7M • Updated • 7
dureduck/1109_lp_2loc_5x4_20samples_b8
Robotics
• 51.7M • Updated • 5
dureduck/1109_lp_2loc_5x4_20samples_b16
Robotics
• 51.7M • Updated • 6
dureduck/1109_lp_2loc_5x4_20samples_b32
Robotics
• 51.7M • Updated • 8
dureduck/eval_so100_act_1109_lp_2loc_5x4_20samples_b32_right_10trials
Updated
dureduck/Olmo-3-7B-PostTraining8K-SFT-step-100
Text Generation
• Updated • 5
dureduck/Olmo-3-7B-PostTraining8K-SFT-step-80
Text Generation
• Updated • 14
dureduck/Olmo-3-7B-PostTraining8K-SFT-step-118
Text Generation
• Updated • 8
dureduck/Olmo-3-7B-PostTraining8K-SFT-step-20
Text Generation
• Updated • 9
dureduck/Olmo-3-7B-PostTraining8K-SFT-step-40
Text Generation
• Updated • 10
dureduck/gemma-3-1b-pt-PostTraining9.8K-SFT
Text Generation
• 1B • Updated • 61
dureduck/gemma-3-1b-it-PostTraining9.8K-SFT-SmallBatch
dureduck/qwen3-4b-base-deepscaler-step19-20260918
Updated
dureduck/gemma-4-26b-a4b-gsm8k-synthetic-cot6144-step1-full-state
Updated
dureduck/gemma-4-26b-a4b-gsm8k-synthetic-cot6144-step2-full-state
Updated
dureduck/gemma4-26b-a4b-gsm8k-synthetic-cot6144-sft-20260916
Updated
dureduck/qwen3-4b-base-deepscaler-sync-grpo-20260917
Updated