-
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
8B • Updated • 1 -
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
2B • Updated • 12 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
8B • Updated • 6 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b
2B • Updated • 12
AI & ML interests
None defined yet.
Recent Activity
View all activity
Ablation datasets for cutoff-based completion experiments.
-
CL-From-Nothing/kukurasu-qwen1.7b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 22 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff1024-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 15 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff2048-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 14 -
CL-From-Nothing/kukurasu-nemotron8b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 13
-
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
8B • Updated • 1 -
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
2B • Updated • 12 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
8B • Updated • 6 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b
2B • Updated • 12
Ablation datasets for cutoff-based completion experiments.
-
CL-From-Nothing/kukurasu-qwen1.7b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 22 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff1024-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 15 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff2048-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 14 -
CL-From-Nothing/kukurasu-nemotron8b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 13
models 80
CL-From-Nothing/Qwen3-4B-OPD-polaris-hard-step40
4B • Updated • 14
CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k4096_lr1e-5
2B • Updated • 16
CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k2048_lr1e-5
2B • Updated • 54
CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k1024_lr1e-5
2B • Updated • 134
CL-From-Nothing/ROSE-token-reward-direct-rlve-step60
Updated
CL-From-Nothing/Qwen3-4B-OPD-polaris-hard-warmup-step40
4B • Updated • 16
CL-From-Nothing/grpo_code_hard_code_rose_sft_25K_warmup-parquet_qwen3-1.7b_epoch_1_mask_resp16384-T1.0-n8
2B • Updated • 21
CL-From-Nothing/rl_warm_up_code_rose_sft_25K_1_7B_SFT-parquet_qwen3-1.7b-base-code-10k-sft_epoch_1_mask_lr1e-5
2B • Updated • 15
CL-From-Nothing/sft_warmup_OpenCodeReasoning_10K-parquet_qwen3-1.7b-base_epoch_1_mask_lr1e-5
2B • Updated • 4
CL-From-Nothing/grpo_pope_rlve_qwen3-1.7b_step_112_resp16384-T1.0-n8
Text Generation • 2B • Updated • 3
datasets 133
CL-From-Nothing/rlve_teacher_topk16_20K
Viewer • Updated • 40k • 27
CL-From-Nothing/rlve_offline_20K
Viewer • Updated • 20k • 35
CL-From-Nothing/rlve_rose_20K
Viewer • Updated • 40k • 35
CL-From-Nothing/rlve_recoverable
Viewer • Updated • 42.1k • 63
CL-From-Nothing/rlve_hard_sampling
Viewer • Updated • 9k • 49
CL-From-Nothing/rose_code
Viewer • Updated • 24.1k • 89
CL-From-Nothing/rlve_hard
Viewer • Updated • 180 • 66
CL-From-Nothing/rlve_rose_opd_4096
Viewer • Updated • 8.98k • 54
CL-From-Nothing/code_rose_sft_25K_1_7B_SFT
Viewer • Updated • 25k • 55
CL-From-Nothing/code_rose_initial_1_7B_SFT_10K_rollouts_Qwen3-4B-Thinking-2507_k12_t0.7_maxtok12288
Viewer • Updated • 87k • 85