JWei05/DAPO-Gemma3-4B-PT-RL-SFT-Data
Updated
Jason Wei
JWei05
·
AI & ML interests
RL, LLMs, DL Theory
Recent Activity
updated a model 29 minutes ago
JWei05/gemma3-4b-pt-sft-distill-from-12b published a model 30 minutes ago
JWei05/gemma3-4b-pt-sft-distill-from-12b updated a model about 1 hour ago
JWei05/gemma3-1b-pt-sft-distill-from-27bOrganizations
JWei05/DAPO-Gemma3-27B-PT-RL-SFT-Data
Updated
JWei05/DAPO-Gemma3-12B-PT-RL-SFT-Data
Updated
JWei05/Nemotron-Cascade-2-SFT-Data-16k-subset
Viewer • Updated • 16.5k • 11
JWei05/Nemotron-Cascade-2-SFT-Data-9k-subset
Viewer • Updated • 9k • 15
JWei05/DAPO-OpenMathInstruct2-34k
Viewer • Updated • 34.8k • 16
JWei05/DAPO-Gemma3-27B-PT-warmup20-step80-SFT-Data
Viewer • Updated • 34.8k • 29
JWei05/DAPO-Gemma4-31B-IT-SFT-Data
Viewer • Updated • 34.8k • 20
JWei05/DAPO-Gemma3-27B-IT-RL-SFT-Data-correct
Viewer • Updated • 41.8k • 28
JWei05/DAPO-Gemma3-27B-IT-RL-SFT-Data
Viewer • Updated • 69.6k • 31
JWei05/swe_smith_py_qwen3.5_35b_trajs_1952
Viewer • Updated • 2k • 56
JWei05/swe_smith_rs_qwen3.5_35b_trajs_2477
Viewer • Updated • 5k • 47
JWei05/swe_smith_go_qwen3.5_35b_trajs_1448
Viewer • Updated • 1.63k • 43
JWei05/swe_smith_js_qwen3.5_35b_trajs_4358
Viewer • Updated • 5k • 53
JWei05/swe_smith_java_qwen3.5_35b_trajs_4369
Viewer • Updated • 5k • 64
JWei05/swe_smith_js_5902_filtered
Viewer • Updated • 5.9k • 32
JWei05/swe_smith_java_6457_filtered
Viewer • Updated • 6.46k • 35
JWei05/swe_smith_rs_4692_filtered
Viewer • Updated • 4.69k • 30
JWei05/swe_smith_py_qwen3.5_35b_trajs_3934_no_p2p
Viewer • Updated • 3.93k • 43
JWei05/swe_smith_go_qwen3.5_35b_trajs_1629_no_p2p
Viewer • Updated • 1.63k • 27
JWei05/swe_smith_py_trajs_2k_incomplete
Viewer • Updated • 2k • 9
JWei05/swe_smith_go_trajs_1629_incomplete
Viewer • Updated • 1.63k • 12
JWei05/SWE-smith-java-6450-filtered
Viewer • Updated • 6.45k • 26
JWei05/SWE-smith-js-4259-filtered
Viewer • Updated • 4.26k • 9
JWei05/SWE-smith-java-6704-filtered-for-problem-statements
Viewer • Updated • 6.7k • 21
JWei05/SWE-smith-go-1629-filtered-for-problem-statements
Viewer • Updated • 1.63k • 52
JWei05/SWE-smith-py-39471-filtered-for-problem-statements
Viewer • Updated • 39.5k • 81
JWei05/Polaris-DeepMath-Dapo-Final-Dataset
Viewer • Updated • 61.7k • 4
JWei05/Polaris-difficulty-1-8-R1-filtered-38K
Viewer • Updated • 37.9k • 4
JWei05/DeepMath-difficulty-9_0
Viewer • Updated • 100 • 5