This collection contains curriculum-RLed Olmo models.
SeanWang0027 PRO
SeanWang0027
AI & ML interests
LLM Post-Training
Recent Activity
updated a dataset about 17 hours ago
SeanWang0027/student_partial_sciworld published a dataset about 17 hours ago
SeanWang0027/student_partial_sciworld updated a model 4 days ago
SeanWang0027/sciworld-online-rose-qwen3-1p7b-5p5Organizations
This contains the SFT-ed Olmo models, and some models built upon.
-
SeanWang0027/olmo-7b-synlogic-survo-sft
7B • Updated • 5 -
SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-sft
7B • Updated • 7 -
SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-math_path-sft
7B • Updated • 4 -
SeanWang0027/sci-10k-olmo-7b-synlogic-survo-space_reasoning-math_path-sft
7B • Updated • 4
This collection contains curriculum-RLed Olmo models.
This contains the SFT-ed Olmo models, and some models built upon.
-
SeanWang0027/olmo-7b-synlogic-survo-sft
7B • Updated • 5 -
SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-sft
7B • Updated • 7 -
SeanWang0027/olmo-7b-synlogic-survo-space_reasoning-math_path-sft
7B • Updated • 4 -
SeanWang0027/sci-10k-olmo-7b-synlogic-survo-space_reasoning-math_path-sft
7B • Updated • 4
models 91
SeanWang0027/sciworld-online-rose-qwen3-1p7b-5p5
2B • Updated • 8
SeanWang0027/sciworld-sft-qwen3-1p7b-from32b
2B • Updated • 10
SeanWang0027/ftb-sciworld-repro
Reinforcement Learning • Updated
SeanWang0027/official-rose-qwen3-1.7b-from-4b-thinking
2B • Updated • 10
SeanWang0027/official-opd-qwen3-1.7b-from-4b-thinking
2B • Updated • 9
SeanWang0027/rose-online-k1024t4096
Updated
SeanWang0027/rlve-distill-scripts
Updated
SeanWang0027/rose-iter-qwen3-1.7b-from-32b-k4096t1024-round2
2B • Updated • 9
SeanWang0027/rose-iter-qwen3-1.7b-from-32b-k4096t1024-round1
2B • Updated • 10
SeanWang0027/rose-online-qwen3-1.7b-from-32b-k4096t4096
2B • Updated • 10
datasets 51
SeanWang0027/student_partial_sciworld
Viewer • Updated • 2.12k • 8
SeanWang0027/sciworld-agentgym-qwen3-1p7b-rollouts
Updated • 41
SeanWang0027/rose-tinker-s25-eval-rollouts
Preview • Updated • 42
SeanWang0027/rose-tinker-step1-rollouts
Viewer • Updated • 256 • 39
SeanWang0027/sciworld-newsplit-rollouts
Updated • 66
SeanWang0027/scienceworld-tcod-split
Viewer • Updated • 3.6k • 52
SeanWang0027/sciworld-teacher32b-sft-partial
Viewer • Updated • 352 • 54
SeanWang0027/rlve-eval-rollouts
Updated • 107
SeanWang0027/rlve-32b-k1024-sft
Viewer • Updated • 9k • 37
SeanWang0027/Multi-Turn
Viewer • Updated • 10 • 620