ilgee/hs2-multiclass-max-ep5-lr5e-6-grpo-ep2-lr2e-6-kl1e-4-rollour512
8B • Updated • 8
ilgee hong
ilgee
AI & ML interests
None yet
Recent Activity
updated a model about 16 hours ago
opsd-genrm/SDRM-Qwen3-30B-A3B-mask70 upvoted a paper about 16 hours ago
Training LLM Judges from Language Feedback via Position-Selective Self-Distillation submitted a paper about 16 hours ago
Training LLM Judges from Language Feedback via Position-Selective Self-DistillationOrganizations
ilgee/hs2-naive-binary-min-ep5-lr1e-5
8B • Updated • 6
ilgee/hs2-naive-binary-max-ep5-lr1e-5
8B • Updated • 6
ilgee/hs2-naive-binary-max-ep10-lr1e-5
8B • Updated • 4
ilgee/hs2-naive-binary-min-ep10-lr1e-5
8B • Updated • 5
ilgee/hs2-naive-multiclass-min-ep10-lr5e-6
8B • Updated • 5
ilgee/hs2-naive-multiclass-min-ep5-lr5e-6
8B • Updated • 3
ilgee/hs2-naive-multiclass-max-ep5-lr5e-6
8B • Updated • 4
ilgee/hs2-naive-multiclass-max-ep10-lr5e-6
8B • Updated • 8
ilgee/Binary-CoT-GenRM-groundtruth-8B
8B • Updated • 4
ilgee/Binary-CoT-GenRM-8B
8B • Updated • 6
ilgee/hs2-naive-binary-min-ep3-lr1e-5
8B • Updated • 4
ilgee/hs2-naive-binary-max-ep3-lr1e-5
8B • Updated • 4
ilgee/hs2-naive-multiclass-min-ep3-lr5e-6
8B • Updated • 6
ilgee/hs2-naive-multiclass-max-ep3-lr5e-6
8B • Updated • 9
ilgee/MetaMath-Mistral-7B-DFT2
Text Generation • 7B • Updated • 10 • 1
ilgee/MetaMath-Mistral-7B-DFT
Text Generation • 7B • Updated • 10