Active filters: ilgee
ilgee/MetaMath-Mistral-7B-DFT
Text Generation • 7B • Updated • 12
ilgee/MetaMath-Mistral-7B-DFT2
Text Generation • 7B • Updated • 15
• 1
ilgee/hs2-naive-multiclass-max-ep3-lr5e-6
8B • Updated • 3
ilgee/hs2-naive-multiclass-max-ep5-lr5e-6
8B • Updated • 1
ilgee/hs2-naive-multiclass-min-ep3-lr5e-6
8B • Updated • 1
ilgee/hs2-naive-multiclass-min-ep5-lr5e-6
8B • Updated • 1
ilgee/hs2-naive-multiclass-min-ep10-lr5e-6
8B • Updated • 4
ilgee/hs2-naive-multiclass-max-ep10-lr5e-6
8B • Updated • 3
ilgee/hs2-naive-binary-max-ep10-lr1e-5
8B • Updated • 1
ilgee/hs2-naive-binary-min-ep10-lr1e-5
8B • Updated • 2
ilgee/hs2-naive-binary-min-ep5-lr1e-5
8B • Updated • 1
ilgee/hs2-naive-binary-max-ep5-lr1e-5
8B • Updated • 8
ilgee/hs2-naive-binary-max-ep3-lr1e-5
8B • Updated • 1
ilgee/hs2-naive-binary-min-ep3-lr1e-5
8B • Updated • 1
ilgee/Binary-CoT-GenRM-groundtruth-8B
8B • Updated • 3
ilgee/Multiclass-CoT-GenRM-groundtruth-8B
8B • Updated • 4
• 1
ilgee/Binary-CoT-GenRM-8B
8B • Updated • 3
ilgee/hs2-multiclass-max-ep5-lr5e-6-grpo-ep2-lr2e-6-kl1e-4-rollour512
8B • Updated • 1
ilgee/hs2-naive-multiclass-max-ep5-lr5e-6-grpo-ep2-lr2e-6-kl1e-4-rollout512-half-v0
8B • Updated • 4
8B • Updated • 26
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-multiclass
8B • Updated • 3
ilgee/Multiclass-CoT-GenRM-8B
8B • Updated • 2
ilgee/hs2-naive-binary-min-ep5-lr1e-5-grpo-ep1-lr2e-6-kl1e-4-rollout512-v0
8B • Updated • 1
ilgee/Multiclass-Think-RM-8B
8B • Updated • 13
ilgee/BT-hs2-naive-multiclass-ep5-lr1e-5
8B • Updated • 3
ilgee/BT-hs2-naive-binary-ep3-lr1e-5
8B • Updated • 1
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-BT
8B • Updated • 4
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-binary
8B • Updated • 3
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-groundtruth
8B • Updated • 1
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-generated
8B • Updated • 1