models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
PathFinder-PRM-7B-i1-GGUFvioletxi_-_ak-prm-full-sft_lr1e-5_wa0.03_balanced_checkpoint3900-ggufvioletxi_-_ak_prm_lr1e-5_wa0.03_balanced_checkpoint2900-ggufvioletxi_-_ak_prm_lr1e-5_wa0.03_balanced_checkpoint2200-ggufvioletxi_-_ak-prm-sub2k_sft-steptok_lr1e-5_wa0.03_balanced_checkpoint1800-ggufDongfuJiang_-_prm_gsm_2k_with_full_sol_mix_ref_redistribution_hf-ggufvioletxi_-_ak_prm_lr1e-5_wa0.03_balanced_checkpoint6100-ggufLlama3.1-8B-PRM-Deepseek-Data-GGUFvioletxi_-_ak_prm_lr1e-6_wa0.03_checkpoint1000-ggufvioletxi_-_ak_prm_lr1e-5_wa0.03_balanced_checkpoint5400-ggufR-PRM-7B-DPO-i1-GGUFLlama3.1-8B-PRM-Mistral-Data-i1-GGUFvioletxi_-_ak_prm_lr1e-6_wa0.03_checkpoint4300-ggufvioletxi_-_ak_prm_lr1e-5_wa0.03_checkpoint180-ggufvioletxi_-_ak_prm_lr1e-5_wa0.03_checkpoint6000-ggufvioletxi_-_ak_prm_lr1e-6_wa0.03_checkpoint3100-ggufvioletxi_-_ak_prm_lr3e-5_wa0.1_checkpoint3000-ggufReasonFlux-PRM-Qwen-2.5-7B-i1-GGUFQwen-VL-PRM-3B-i1-GGUFmath-shepherd-mistral-7b-prm-GGUFQwen-VL-PRM-7B-i1-GGUFDongfuJiang_-_prm_version2_subsample_no_ref_hf-ggufDongfuJiang_-_prm_version2_subsample_hf-ggufPRM-Math-7B-Reasoner-i1-GGUFQwen-VL-PRM-7B-GGUFDongfuJiang_-_prm_version3_full_hf-ggufDongfuJiang_-_prm_version3_subsample_no_ref_hf-ggufDongfuJiang_-_prm_gsm_2k_with_full_sol_mix_ref_error_only_hf-ggufDongfuJiang_-_prm_gsm_all_data_bon_4_hf-ggufQwen2.5-7B-PURE-PRM-GGUF