This collection contains curriculum-RLed Olmo models.
SeanWang0027 PRO
SeanWang0027
AI & ML interests
Continual Learning
Recent Activity
upvoted a paper 3 days ago
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? updated a model 4 days ago
CL-From-Nothing/teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b published a model 4 days ago
CL-From-Nothing/teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7bOrganizations
models 27
SeanWang0027/sdft_minesweeper_kukurasu_Qwen3-1.7B_1_epoch_8192_32_batch_2e-5_lr
2B • Updated • 7
SeanWang0027/sdft_sudoku_minesweeper_kukurasu_Nemotron-Cascade-8B_1_epoch_8192_32_batch_2e-5_lr
8B • Updated • 4
SeanWang0027/sdft_minesweeper_5K_kukurasu_9K_Nemotron-Cascade-8B_1_epoch_8192_32_batch_2e-5_lr
8B • Updated • 13
SeanWang0027/sdft_kukurasu_9K_Nemotron-Cascade-8B_1_epoch_8192_32_batch_2e-5_lr
8B • Updated • 12
SeanWang0027/sdft_sudoku_7K_Nemotron-Cascade-8B_1_epoch_8192_32_batch_2e-5_lr
8B • Updated • 13
SeanWang0027/sdft_kukurasu_9K_Qwen3-1.7B_1_epoch_8192_32_batch_2e-5_lr
2B • Updated • 8
SeanWang0027/sdft_sudoku_7K_Qwen3-1.7B_1_epoch_8192_32_batch_2e-5_lr
2B • Updated • 14
SeanWang0027/sdft_minesweeper_5K_Qwen3-1.7B_1_epoch_8192_32_batch_2e-5_lr
2B • Updated • 13
SeanWang0027/sdft_minesweeper_5K_1_epoch_8192_32_batch_2e-5_lr
8B • Updated • 12
SeanWang0027/medical_o1-20k-olmo-7b-synlogic-survo-space_reasoning-math_path-grpo
7B • Updated
datasets 12
SeanWang0027/mixed_sft_RLVE_Qwen3_4B_Thinking_2507
Viewer • Updated • 16k • 12
SeanWang0027/roofline_sft_RLVE_Qwen3_4B_Thinking_2507
Viewer • Updated • 13.8k • 11
SeanWang0027/sdft_data
Viewer • Updated • 21.6k • 14
SeanWang0027/roofline
Viewer • Updated • 21.6k • 15
SeanWang0027/sudoku_reasoning_offline
Viewer • Updated • 14.1k • 6
SeanWang0027/eval_data
Viewer • Updated • 277k • 114
SeanWang0027/sft-training-data
Viewer • Updated • 34.8k • 50
SeanWang0027/mmlu_pro_medical
Viewer • Updated • 1.54k • 15
SeanWang0027/mmlu_pro_subset_test
Viewer • Updated • 700 • 18
SeanWang0027/synlogic
Viewer • Updated • 24k • 55