rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm12k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_fixed_prm16k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm1k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm20k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm2k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm24k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm28k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm4k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm1k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm8k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm2k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm4k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_fixed_prm16k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm8k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_fixed_prm16k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_self_prm_layer2_dim2048_head64_e3_lr5e-5_pos7 Updated Sep 3, 2025
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_self_prm_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 3, 2025
rediska0123/ue_manager_proofnet_uhead_claim_Qwen3-8B_self_prm_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 3, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_self_prm_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 3, 2025
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_self_prm_layer2_dim2048_head64_e3_lr5e-5_pos7 Updated Sep 3, 2025
rediska0123/ue_manager_gsm8k_uhead_claim_Qwen3-8B_self_prm_layer2_dim2048_head64_e3_lr5e-5_pos7 Updated Sep 3, 2025
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_fixed_prm_layer1_dim1024_head32_e5_lr1e-4_pos7 Updated Sep 2, 2025
rediska0123/ue_manager_math_no_prm800k_uhead_claim_Qwen3-8B_fixed_prm_layer1_dim512_head16_e5_lr5e-4_pos7 Updated Sep 2, 2025