-
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
8B • Updated • 3 -
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
2B • Updated • 6 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
8B • Updated • 3 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b
2B • Updated • 3
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 • 10 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff1024-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 11 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff2048-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 7 -
CL-From-Nothing/kukurasu-nemotron8b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 8
-
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
8B • Updated • 3 -
CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
2B • Updated • 6 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
8B • Updated • 3 -
CL-From-Nothing/student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b
2B • Updated • 3
Ablation datasets for cutoff-based completion experiments.
-
CL-From-Nothing/kukurasu-qwen1.7b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 10 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff1024-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 11 -
CL-From-Nothing/kukurasu-qwen1.7b-cutoff2048-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 7 -
CL-From-Nothing/kukurasu-nemotron8b-cutoff512-completed-by-qwen3-4b-thinking-r16384
Viewer • Updated • 20k • 8
models 76
CL-From-Nothing/grpo_code_hard_code_rose_sft_25K_warmup-parquet_qwen3-1.7b_epoch_1_mask_resp16384-T1.0-n8
2B • Updated • 2
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 • 9
CL-From-Nothing/sft_warmup_OpenCodeReasoning_10K-parquet_qwen3-1.7b-base_epoch_1_mask_lr1e-5
2B • Updated • 11
CL-From-Nothing/grpo_pope_rlve_qwen3-1.7b_step_112_resp16384-T1.0-n8
Text Generation • 2B • Updated • 13
CL-From-Nothing/opd_rlve_offline_20K_qwen3-1.7b_k4096_qwen3-4b-think_resp16384-T1.0-n8-topk16-step70
2B • Updated • 18
CL-From-Nothing/grpo_rlve_offline_20K_qwen3-1.7b_k4096_resp16384-T1.0-n8-bs128-step70
2B • Updated • 16
CL-From-Nothing/grpo_code_hard_qwen3-1.7b
2B • Updated • 18
CL-From-Nothing/opd_code_hard_qwen3-1.7b
2B • Updated • 20
CL-From-Nothing/rl_warm_up_code_rose_sft_25K-parquet_qwen3-1.7b_epoch_1_mask
2B • Updated • 17
CL-From-Nothing/opd_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_qwen3-4b-think_resp16384-T1.0-n8-topk16
2B • Updated • 16
datasets 130
CL-From-Nothing/code_rose_sft_25K_1_7B_SFT
Viewer • Updated • 25k • 19
CL-From-Nothing/code_rose_initial_1_7B_SFT_10K_rollouts_Qwen3-4B-Thinking-2507_k12_t0.7_maxtok12288
Viewer • Updated • 87k • 27
CL-From-Nothing/code_rose_initial_1_7B_SFT_10K
Viewer • Updated • 7.25k • 26
CL-From-Nothing/OpenCodeReasoning_10K
Viewer • Updated • 10k • 25
CL-From-Nothing/rose_code_4B
Viewer • Updated • 21.5k • 20
CL-From-Nothing/pope_rlve_1_7B
Viewer • Updated • 14.4k • 23
CL-From-Nothing/rlve_offline_20K_POPE_prefix_pass1_qwen3-1.7b
Viewer • Updated • 20k • 34
CL-From-Nothing/rlve_offline_20K_POPE_prefix
Viewer • Updated • 20k • 27
CL-From-Nothing/code-eval-pass8-rollouts
Viewer • Updated • 16.3k • 48
CL-From-Nothing/rose_code_samples
Viewer • Updated • 244k • 55