PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advprm-n5-eta200-stepLen256-stepSplit-length-step300 4B • Updated 6 days ago • 9
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advprm-n5-eta200-stepLen256-stepSplit-length-step250 4B • Updated 6 days ago • 11
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advprm-n5-eta200-stepLen256-stepSplit-length-step400 4B • Updated 7 days ago • 5
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advprm-n5-eta200-stepLen256-stepSplit-length-step400 4B • Updated 7 days ago • 5
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advprm-n5-eta200-stepLen256-stepSplit-length-step300 4B • Updated 6 days ago • 9
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advprm-n5-eta200-stepLen256-stepSplit-length-step250 4B • Updated 6 days ago • 11
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advorm-n5-eta200-stepLen256-stepSplit-length-step250 4B • Updated 7 days ago • 9
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta200-stepLen256-stepSplit-length-step250 1B • Updated 7 days ago • 8
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta200-stepLen256-stepSplit-length-step250 1B • Updated 7 days ago • 8
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advorm-n5-eta200-stepLen256-stepSplit-length-step250 4B • Updated 7 days ago • 9
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advorm-n5-eta100-stepLen256-stepSplit-nn-step200 4B • Updated 10 days ago • 7
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advorm-n5-eta100-stepLen256-stepSplit-nn-step200 4B • Updated 10 days ago • 7
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advorm-n5-eta0-stepLen0-stepSplit-nn-step200 4B • Updated 10 days ago • 10
PRM-CoT/Llama-3.2-3B-Instruct-numina-grpo-prm_advorm-n5-eta0-stepLen0-stepSplit-nn-step200 4B • Updated 10 days ago • 10
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta0-stepLen0-stepSplit-nn-step500 1B • Updated 11 days ago • 10
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta0-stepLen0-stepSplit-nn-step500 1B • Updated 11 days ago • 10
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta100-stepLen256-stepSplit-nn-step500 1B • Updated 11 days ago • 10
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta100-stepLen256-stepSplit-nn-step500 1B • Updated 11 days ago • 10
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta100-stepLen256-stepSplit-nn-step400 1B • Updated 11 days ago • 9
PRM-CoT/Llama-3.2-1B-Instruct-numina-grpo-prm_advorm-n5-eta100-stepLen256-stepSplit-nn-step400 1B • Updated 11 days ago • 9