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.
Llama3.1-8B-PRM-Deepseek-Datamath-shepherd-mistral-7b-prmqwen3-4b-sft-prmmath-shepherd-mistral-7b-prm-GGUFLlama-PRM800Kgranite-3.3-8b-math-prm-v2Llama3.1-8B-PRM-Mistral-DataReasonFlux-PRM-7Baligntune-testrun-PRMweb-alf-sci_15106_241696_prm_data_train-llama3-8b-sft_16_mseQwen3-4B-DPO-prm-pairstulu-v2.5-dpo-13b-prm-phase-2Deepthink-1.5B-Open-PRMPathFinder-PRM-7BReasonFlux-PRM-1.5Bprm_version3_full_hfQwen2.5-3b-spare-prm-mathPRM-Math-7B-ReasonerUniversal-PRM-7Bllemma-7b-sft-prm800k-level-1to3-hfQwen-PRM800Kqwen3-8b-full-sft-prm-r2egym-swebench-k5-opus-distill-32k-lr5e6-multiturnprm800k_llama_fulltuneReasonFlux-PRM-Qwen-2.5-7Bprm_version3_subsample_hfprm_gsm_2k_with_full_sol_mix_ref_remove_all_correct_hfDeepthink-1.5B-Open-PRM-Q8_0-GGUFprm_gsm_2k_with_full_sol_mix_ref_redistribution_hfqwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_thinkqwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-flattened