yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110
4B • Updated • 75
Choi
yunhowhour
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
KL for a KL: On-Policy Distillation with Control Variate Baseline upvoted a paper about 14 hours ago
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States updated a model 5 days ago
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110Organizations
None yet
models 11
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_90
4B • Updated • 57
yunhowhour/Distill-1.5B_GRESO_batch_512_step_120
2B • Updated • 50
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_90
4B • Updated • 44
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_80
4B • Updated • 57
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_70
4B • Updated • 11
yunhowhour/Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_60
4B • Updated • 157
yunhowhour/CRRL_distill_1.5B_w_o_globalnorm_step_120
2B • Updated • 90
yunhowhour/CRRL_distill_1.5B_GRESO_step_90
2B • Updated • 70
yunhowhour/CRRL_batch_1024_step_50
4B • Updated • 99
datasets 0
None public yet