Qwen2.5 VL 3B RL Checkpoints
yangneng chen
ynchen11
AI & ML interests
None yet
Organizations
None yet
models 17
ynchen11/7b_high_0.28_EBA_true_alpha_0.4_kappa_2.0_SFT_0.12_perc0.0_entropy_0.0_step_202
8B • Updated
ynchen11/7b_high_0.28_EBA_true_alpha_0.4_kappa_2.0_SFT_0.12_perc0.4_entropy_0.2_step200
8B • Updated
ynchen11/7b_high_0.28_EBA_false_SFT_0.10_perc0.4_entropy_0.4_step202
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_true_alpha_0.4_kappa_2.0_SFT_0.06_step190
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_false_SFT_0.12_perc0.0_entropy_0.0_ep2_step202
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_false_SFT_0.12_perc0.2_entropy_0.4_step_202
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_false_SFT_0.08_perc0.4_entropy_0.2_ep2_step202
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_false_SFT_0.10_perc0.4_entropy_0.2_step_202
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_false_SFT_0.10_perc0.2_entropy_0.4_step_250
8B • Updated
ynchen11/qwen2_5_vl_7b__dapo_clip_high_0.28_EBA_false_SFT_0.08_perc0.4_entropy_0.4_step_202
8B • Updated