AI & ML interests
None yet
Organizations
None yet
3B • Updated • 2
• 1
ilgee/Multiclass-Think-RM-8B
8B • Updated • 2
8B • Updated • 4
ilgee/qwen2.5-3b-inst-hs2-naive-binary-max-ep7-lr1e-5
3B • Updated • 1
ilgee/qwen2.5-3b-inst-hs2-bt-rm-ep2-lr1e-5
3B • Updated ilgee/qwen2.5-3b-inst-hs2-naive-binary-max-ep10-lr1e-5
3B • Updated ilgee/qwen2.5-3b-inst-hs2-naive-binary-cot-generated-ep10-lr1e-5
3B • Updated ilgee/Llama-3.1-8B-Instruct-grpo-ep1-lr1e-6-kl1e-4-rollout256-0.03-0.03
8B • Updated • 1
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-generated
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-binary
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-BT
ilgee/Llama-3.1-8B-Instruct-grpo-ep2-lr2e-6-kl1e-4-rollout512-0.03-multiclass
ilgee/BT-hs2-naive-binary-ep3-lr1e-5
ilgee/BT-hs2-naive-multiclass-ep5-lr1e-5
8B • Updated • 1