rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_self_fixed_prm_hs_20e_e2 Updated 5 days ago
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_self_fixed_prm_feature_ablation_hs_20e_best_at_epoch2 Updated 5 days ago
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_self_fixed_prm_feature_ablation_hs_20e_best_at_epoch2 Updated 6 days ago
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_hs_20e_best_at_epoch4 Updated 6 days ago
rediska0123/uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_hs_20e_best_at_epoch4 Updated 6 days ago • 3
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_hs_20e_best_at_epoch4 Updated 12 days ago
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_hs_20e_best_at_epoch4 Updated 12 days ago
rediska0123/ue_manager_eval_uhead_claim_Qwen3-8B_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3 Updated Sep 24
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_lookbacklens Updated Sep 23