menik1126/OVD-Math-1-data-RLVR-Step300-Retrain
2B • Updated • 11
OVD
OVD paper checkpoints: 1-data and 128-data training, Full response, High-entropy suffix, Random suffix, and RLVR baselines.
-
-
menik1126/OVD-Math-1-data-RLVR-Step500
2B • Updated • 10 -
menik1126/OVD-Math-1-data-RLVR-Step600
2B • Updated • 7 -
menik1126/OVD-Math-1-data-RLVR-Step800
2B • Updated • 9 -
menik1126/OVD-Math-128-data-FR-Step300-Historical
2B • Updated • 10 -
menik1126/OVD-Math-128-data-FR-Step500-Historical
2B • Updated • 11 -
menik1126/OVD-Math-128-data-FR-Step600-Historical
2B • Updated • 16 -
menik1126/OVD-Math-128-data-FR-Step800-Historical
2B • Updated • 8 -
menik1126/OVD-Math-128-data-HES-Step300-Historical
2B • Updated • 16 -
menik1126/OVD-Math-128-data-HES-Step500-Historical
2B • Updated • 14 -
menik1126/OVD-Math-128-data-HES-Step600-Historical
2B • Updated • 11 -
menik1126/OVD-Math-128-data-HES-Step800-Historical
2B • Updated • 8 -
menik1126/OVD-Math-128-data-RS-Step300-Historical
2B • Updated • 19 -
menik1126/OVD-Math-128-data-RS-Step500-Historical
2B • Updated • 9 -
menik1126/OVD-Math-128-data-RS-Step600-Historical
2B • Updated • 14 -
menik1126/OVD-Math-128-data-RS-Step800-Historical
2B • Updated • 16 -
menik1126/OVD-Math-128-data-RLVR-Step300
2B • Updated • 11 -
menik1126/OVD-Math-128-data-RLVR-Step500
2B • Updated • 10 -
menik1126/OVD-Math-128-data-RLVR-Step600
2B • Updated • 8 -
menik1126/OVD-Math-128-data-RLVR-Step800
2B • Updated • 9 -
menik1126/OVD-Math-1-data-FR-Step300-Historical
Text Generation • 2B • Updated • 246 -
menik1126/OVD-Math-1-data-FR-Step500-Historical
Text Generation • 2B • Updated • 245 -
menik1126/OVD-Math-1-data-FR-Step600-Historical
Text Generation • 2B • Updated • 240 -
menik1126/OVD-Math-1-data-FR-Step800-Historical
Text Generation • 2B • Updated • 235 -
menik1126/OVD-Math-1-data-HES-Step300-Historical
Text Generation • 2B • Updated • 233 -
menik1126/OVD-Math-1-data-HES-Step500-Historical
Text Generation • 2B • Updated • 236 -
menik1126/OVD-Math-1-data-HES-Step600-Historical
Text Generation • 2B • Updated • 219 -
menik1126/OVD-Math-1-data-HES-Step800-Historical
Text Generation • 2B • Updated • 226 -
menik1126/OVD-Math-1-data-RS-Step300-Historical
Text Generation • 2B • Updated • 233 -
menik1126/OVD-Math-1-data-RS-Step500-Historical
Text Generation • 2B • Updated • 215 -
menik1126/OVD-Math-1-data-RS-Step600-Historical
Text Generation • 2B • Updated • 206 -
menik1126/OVD-Math-1-data-RS-Step800-Historical
Text Generation • 2B • Updated • 221
menik1126/OVD-Web-Qwen2.5-3B-reject5-Step200
Text Generation • 3B • Updated • 76Note Web Qwen2.5-3B Base, pure Query Reject5, step200