menik1126/ovd-math-1-data-rlvr-step300
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 • 8 -
menik1126/ovd-math-1-data-rlvr-step600
2B • Updated • 6 -
menik1126/ovd-math-1-data-rlvr-step800
2B • Updated • 7 -
menik1126/ovd-math-128-data-full-step300-historical
2B • Updated • 8 -
menik1126/ovd-math-128-data-full-step500-historical
2B • Updated • 10 -
menik1126/ovd-math-128-data-full-step600-historical
2B • Updated • 15 -
menik1126/ovd-math-128-data-full-step800-historical
2B • Updated • 6 -
menik1126/ovd-math-128-data-hes-step300-historical
2B • Updated • 14 -
menik1126/ovd-math-128-data-hes-step500-historical
2B • Updated • 8 -
menik1126/ovd-math-128-data-hes-step600-historical
2B • Updated • 9 -
menik1126/ovd-math-128-data-hes-step800-historical
2B • Updated • 6 -
menik1126/ovd-math-128-data-random-step300-historical
2B • Updated • 12 -
menik1126/ovd-math-128-data-random-step500-historical
2B • Updated • 7 -
menik1126/ovd-math-128-data-random-step600-historical
2B • Updated • 12 -
menik1126/ovd-math-128-data-random-step800-historical
2B • Updated • 15 -
menik1126/ovd-math-128-data-rlvr-step300
2B • Updated • 9 -
menik1126/ovd-math-128-data-rlvr-step500
2B • Updated • 6 -
menik1126/ovd-math-128-data-rlvr-step600
2B • Updated • 6 -
menik1126/ovd-math-128-data-rlvr-step800
2B • Updated • 7 -
menik1126/ovd-math-1-data-full-step300-historical
Text Generation • 2B • Updated • 233 -
menik1126/ovd-math-1-data-full-step500-historical
Text Generation • 2B • Updated • 232 -
menik1126/ovd-math-1-data-full-step600-historical
Text Generation • 2B • Updated • 224 -
menik1126/ovd-math-1-data-full-step800-historical
Text Generation • 2B • Updated • 221 -
menik1126/ovd-math-1-data-hes-step300-historical
Text Generation • 2B • Updated • 220 -
menik1126/ovd-math-1-data-hes-step500-historical
Text Generation • 2B • Updated • 219 -
menik1126/ovd-math-1-data-hes-step600-historical
Text Generation • 2B • Updated • 200 -
menik1126/ovd-math-1-data-hes-step800-historical
Text Generation • 2B • Updated • 214 -
menik1126/ovd-math-1-data-random-step300-historical
Text Generation • 2B • Updated • 215 -
menik1126/ovd-math-1-data-random-step500-historical
Text Generation • 2B • Updated • 200 -
menik1126/ovd-math-1-data-random-step600-historical
Text Generation • 2B • Updated • 192 -
menik1126/ovd-math-1-data-random-step800-historical
Text Generation • 2B • Updated • 207 -
menik1126/ovd-web-pure-cot-reject-step200
Text Generation • 3B • Updated • 130 -
menik1126/ovd-web-query-cot-reject-step200
Text Generation • 3B • Updated • 124
menik1126/ovd-web-qwen25-3b-base-query-reject5-step200
Text Generation • 3B • Updated • 70Note Web Qwen2.5-3B Base, pure Query Reject5, step200