rediska0123/qwen25-math-prm-lora-step-continuation-2epochs Feature Extraction • 7B • Updated Mar 15 • 8
rediska0123/qwen25-math-prm-lora-correctness-5epochs-lr2e-5 Feature Extraction • 7B • Updated Mar 15 • 4
rediska0123/qwen25-math-prm-lora-correctness-5epochs-lr2e-4 Feature Extraction • 7B • Updated Mar 15 • 4
rediska0123/ue_manager_trip_uhead_token_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7 Updated Jan 3
rediska0123/ue_manager_meet_uhead_token_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7 Updated Jan 2
rediska0123/ue_manager_calendar_uhead_token_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7 Updated Jan 2
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_attn Updated Dec 19, 2025
rediska0123/ue_manager_math_uhead_token_Qwen3-8B_fixed_prm_feature_hs_20e_best_at_epoch2 Updated Dec 9, 2025
rediska0123/ue_manager_proofnet_uhead_token_Qwen3-8B_fixed_prm_feature_hs_20e_best_at_epoch2 Updated Dec 9, 2025
rediska0123/ue_manager_gsm8k_uhead_token_Qwen3-8B_fixed_prm_feature_hs_20e_best_at_epoch2 Updated Dec 9, 2025
rediska0123/ue_manager_math_uhead_claim_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7 Updated Dec 9, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7 Updated Dec 9, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm_feature_linear_hs_20e_best_at_epoch7 Updated Dec 9, 2025