Checkpoints for the PTS paper (adaptive RLVR->RLCR switching) and DCPO/CSR baselines compared against it.
hwang
juwon1105
AI & ML interests
None yet
Recent Activity
updated a collection 6 days ago
PTS (paper) updated a model 6 days ago
juwon1105/PTS-DCPO-qwen3-1.7B-bigmath5000-ptscompare published a model 6 days ago
juwon1105/PTS-DCPO-qwen3-1.7B-bigmath5000-ptscompareOrganizations
None yet
models 71
juwon1105/PTS-DCPO-qwen3-1.7B-bigmath5000-ptscompare
2B • Updated • 14
juwon1105/PTS-DCPO-qwen3-1.7B-bigmath5000-buggy
2B • Updated • 13
juwon1105/PTS-qwen3-1.7B-hotpot5000-main
2B • Updated • 12
juwon1105/PTS-qwen3-0.6B-bigmath5000-main
0.6B • Updated • 12
juwon1105/PTS-llama32-3B-bigmath5000-main
Text Generation • Updated • 11
juwon1105/PTS-qwen3-1.7B-bigmath5000-main-seed44
2B • Updated • 12
juwon1105/PTS-qwen3-1.7B-bigmath5000-main-seed42
2B • Updated • 16
juwon1105/PTS-qwen3-1.7B-bigmath5000-hardswitch2500
2B • Updated • 17
juwon1105/PTS-qwen3-1.7B-bigmath5000-hardswitch1000-brier075
2B • Updated • 12
juwon1105/PTS-qwen3-1.7B-bigmath5000-hardswitch1000-brier025
2B • Updated • 15