L1nkee/qwen3-4b-base-grpo-rollout-dapo17k-think-lr1e-6-kl1e-3-clip0.2-s42
Text Generation • Updated • 4
Yu Yang PRO
L1nkee
AI & ML interests
None yet
Recent Activity
updated a model about 22 hours ago
L1nkee/qwen3-4b-base-grpo-rollout-dapo17k-think-lr1e-6-kl1e-3-clip0.2-s42 updated a model about 22 hours ago
L1nkee/qwen3-4b-base-grpo-actorold-dapo17k-think-lr1e-6-kl1e-3-clip0.2-s43 published a model 1 day ago
L1nkee/qwen3-4b-base-grpo-rollout-dapo17k-think-lr1e-6-kl1e-3-clip0.2-s42Organizations
models 18
L1nkee/qwen3-4b-base-grpo-actorold-dapo17k-think-lr1e-6-kl1e-3-clip0.2-s43
Text Generation • Updated • 7
L1nkee/qwen3-4b-base-grpo-actorold-dapo17k-think-lr1e-6-kl1e-3-clip0.2-s42
Text Generation • Updated • 22
L1nkee/Qwen3-4B-Base-NoThink-DAPO-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 47
L1nkee/Qwen3-4B-Base-Think-GRPO-ClipHigher0.28-KL0.001-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 61
L1nkee/Qwen3-4B-Base-NoThink-GSPO-KL0-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 51
L1nkee/Qwen3-4B-Base-Think-GRPO-KL0.001-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 51
L1nkee/Qwen3-4B-NoThink-DPPO-BinaryTV-delta0.2-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 57
L1nkee/Qwen3-4B-NoThink-DAPO-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 58
L1nkee/Qwen3-4B-NoThink-GRPO-KL0.001-LR1e-5-bf16-540steps
Reinforcement Learning • 4B • Updated • 58
datasets 0
None public yet