yongchanskii/qwen3-4b-opd-unke-merge_student_ce_0.02_step_5_traj_len_4096_bf10_ckpt_5000 Text Generation • 4B • Updated Aug 17 • 141
yongchanskii/qwen3-4b-opd-unke-merge_student_ce_0.02_step_5_traj_len_4096_bf10_ckpt_5000 Text Generation • 4B • Updated Aug 17 • 141
yongchanskii/smollm3-3b-opd-unke-merge_student_ce_0.02_step_1_traj_len_4096_bf10_ckpt_5000 Text Generation • 3B • Updated Aug 17 • 126
yongchanskii/smollm3-3b-opd-unke-merge_student_ce_0.02_step_1_traj_len_4096_bf10_ckpt_5000 Text Generation • 3B • Updated Aug 17 • 126
yongchanskii/qwen3-4b-opd-zsre-merge_student_ce_0.02_step_5_traj_len_4096_bf10_ckpt_10000 Text Generation • 4B • Updated Aug 17 • 170
yongchanskii/qwen3-4b-opd-zsre-merge_student_ce_0.02_step_5_traj_len_4096_bf10_ckpt_10000 Text Generation • 4B • Updated Aug 17 • 170
yongchanskii/smollm3-3b-opd-zsre-merge_student_ce_0.02_step_1_traj_len_4096_bf10_ckpt-8000 Text Generation • 3B • Updated Aug 16 • 27
yongchanskii/smollm3-3b-opd-zsre-merge_student_ce_0.02_step_1_traj_len_4096_bf10_ckpt-8000 Text Generation • 3B • Updated Aug 16 • 27
yongchanskii/smollm3-3b-opd-zsre-merge_student_ce_0.02_step_1_traj_len_4096_bf10_ckpt-10000 Text Generation • 3B • Updated Aug 16 • 127
yongchanskii/smollm3-3b-opd-zsre-merge_student_ce_0.02_step_1_traj_len_4096_bf10_ckpt-10000 Text Generation • 3B • Updated Aug 16 • 127
yongchanskii/smollm3-3b-opd-zsre-merge_student_ce_0.02_step_25_traj_len_4096_bf10_ckpt-2000 Text Generation • 3B • Updated Aug 14 • 116
yongchanskii/smollm3-3b-opd-zsre-merge_student_ce_0.02_step_25_traj_len_4096_bf10_ckpt-2000 Text Generation • 3B • Updated Aug 14 • 116
LAMAR: An Open Language-Aware Multilingual Alignment Reranker Paper • 2607.22042 • Published Jul 24 • 18
Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation Paper • 2604.08627 • Published Apr 9 • 2