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.
mistral-7b-orpo-capybara-reproduction-GGUFalpaca-7b-reproducedReproduced-tulu2-dpo-13b-i1-GGUFexaone-7b-verireason-reproduced-1513-fullft-best-grpo-reproduced-1.0infoseeker-repro-4b-i1-GGUFARPO-reproduce_Qwen2.5-3B-Instruct_SFT_paper-configsearchr1-repro-4b-i1-GGUFARPO-reproduce_Qwen2.5-3B-Instruct_SFT_code-configLFM2-1.2B-FRMOO-V3K-Repro-BF16-i1-GGUFARPO-reproduce_Qwen3-8B_SFT_paper-configARPO-reproduce_Qwen3-8B_SFT_code-configrepro-rephraser-4Balpaca-8b-reproduced-llama-3-GGUFexaone-7b-verireason-reproduced-1513-fullft-epoch4alpaca-7b-reproduced-GGUFalpaca-7b-reproduced-llama-2-GGUFrepro-rephraser-4B-GGUFclowman_-_openchat-mistral-7b-reproduce-ggufReproduced-tulu2-dpo-13b-GGUFQFFT-repro-LIMO-QFFT-7BQFFT-repro-LIMO-SFT-7BQFFT-repro-S1.1-SFT-7BQFFT-repro-S1.1-QFFT-7Brepro-rephraser-1B-GGUFQWEN3.5-oracul-events_reprocessor-4b-GGUFinfoseeker-repro-4b-GGUFsearchr1-repro-4b-GGUFtailsft-repro-olmo2-1b-stdtailsft-repro-olmo2-1b-tail50rethink_rlvr_reproduce-ground_truth-qwen2.5_math_7b-lr5e-7-kl0.00-step150