-
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
8B • Updated • 2 -
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
2B • Updated • 1 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
8B • Updated • 1 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b
2B • Updated • 1
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 • 14 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff1024-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 12 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff2048-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 11 -
CL-From-Nothing/kukurasu-nemotron8b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 14
-
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
8B • Updated • 2 -
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
2B • Updated • 1 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
8B • Updated • 1 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b
2B • Updated • 1
Ablation datasets for cutoff-based completion experiments.
-
CL-From-Nothing/kukurasu-qwen1.7b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 14 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff1024-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 12 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff2048-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 11 -
CL-From-Nothing/kukurasu-nemotron8b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 14
models 62
CL-From-Nothing/opd_rlve_qwen3-1.7b-SFT-rlve-20K-1epoch_Qwen3-4B-Thinking-2507_resp16384-T1.0-n8-topk16-step70
2B • Updated
CL-From-Nothing/grpo_rlve_qwen3-1.7b-SFT-rlve-20K-1epoch_resp16384-T1.0-n8-bs128-step70
2B • Updated • 12
CL-From-Nothing/rl_warmup_rlve_offline_20K-parquet_qwen3-1.7b_epoch_1_mask
2B • Updated • 14
CL-From-Nothing/opd_rlve_qwen3-1.7b_Qwen3-4B-Thinking-2507_resp16384-T1.0-n8-topk16-step70
2B • Updated • 15
CL-From-Nothing/grpo_rlve_qwen3-1.7b_resp16384-T1.0-n8-step70
2B • Updated • 16
CL-From-Nothing/opd_polaris_hard_full_sft_qwen3-1.7b_resp16384-T1.0-n8-step40
2B • Updated • 19
CL-From-Nothing/opd_polaris_hard_plain_qwen3-1.7b_resp16384-T1.0-n8-step40
2B • Updated • 17
CL-From-Nothing/opd_polaris_hard_polaris_ROSE_warmup_qwen3-1.7b_epoch_1_mask_resp16384-T1.0-n8-topk16-step40
2B • Updated • 16
CL-From-Nothing/grpo_polaris_hard_polaris_POPE_warmup_40K-parquet_qwen3-4b_epoch_1_mask_resp16384-T1.0-n8
4B • Updated • 19
CL-From-Nothing/grpo_polaris_hard_polaris_ROSE_warmup_40K-parquet_qwen3-1.7b_epoch_1_mask_resp16384-T1.0-n8
2B • Updated • 16
datasets 121
CL-From-Nothing/code_hard
Viewer • Updated • 10.1k
CL-From-Nothing/code_full_sft_hard_25K
Viewer • Updated • 25k
CL-From-Nothing/rose_code_samples
Preview • Updated
CL-From-Nothing/rlve_rose_20K
Viewer • Updated • 20k
CL-From-Nothing/rlve_rose_initial_pass3
Viewer • Updated • 26.9k
CL-From-Nothing/rose_code-Qwen3-1.7B-Pass8-Rollouts
Viewer • Updated • 3.26k • 30
CL-From-Nothing/RLVE-Test-Qwen3-1.7B-SFT-warmup-Pass8
Viewer • Updated • 1.44k • 22
CL-From-Nothing/RLVE-Test-Qwen3-1.7B-GRPO-step70-Pass8
Viewer • Updated • 1.44k • 23
CL-From-Nothing/rose_code
Viewer • Updated • 24.1k • 42
CL-From-Nothing/rlve_rose_initial_pass8
Viewer • Updated • 71.9k • 23