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-iterative-DPO-final-ExPOLlama3-v2-iterative-DPO-iter2-i1-GGUFLLaMA-3-8B-SFR-Iterative-DPO-R-i1-GGUFLLaMA3-iterative-DPO-final-i1-GGUFSFR-Iterative-DPO-LLaMA-3-8B-R-i1-GGUFLlama3-v2-iterative-DPO-iter3-i1-GGUFLlama3-v2-iterative-DPO-iter1-i1-GGUFLlama3-v2-iterative-DPO-iter1-GGUFLLaMA-3-8B-SFR-Iterative-DPO-R-GGUFLLaMA3-iterative-DPO-final-GGUFSFR-Iterative-DPO-LLaMA-3-8B-R-GGUFLLaMA-3-8B-SFR-Iterative-DPO-Concise-R-i1-GGUFLlama3-v2-iterative-DPO-iter3-GGUFLlama3-v2-iterative-DPO-iter2-GGUFLLaMA-3-8B-SFR-Iterative-DPO-Concise-R-GGUFLLaMA3-iterative-DPO-final-ExPO-GGUFLLaMA3-iterative-DPO-final-ExPO-i1-GGUFmistral-irl-iter2-iterative-dpo-GGUFLLaMA3-iterative-DPO-final-ExPO-GGUFLLaMA3-iterative-DPO-final-ExPO-Q5_K_M-GGUFSFR-Iterative-DPO-LLaMA-3-8B-R-Q4_K_M-GGUFllama32-1b-iterative-dpoqwen_2.5_7b-cleanup_lion_dpo_after_ft_numbers_iterativeDeepJudge_fullPromptqwen_2.5_7b-cleanup_panda_dpo_after_ft_numbers_iterativeDeepJudge_fullPromptqwen_2.5_7b-cleanup_cat_dpo_after_ft_numbers_iterativeDeepJudge_fullPromptqwen_2.5_7b-cleanup_cat_dpo_numbers_iterativeDeepJudge_fullPromptqwen_2.5_7b-cleanup_panda_dpo_numbers_iterativeDeepJudge_fullPromptqwen_2.5_7b-cleanup_lion_dpo_numbers_iterativeDeepJudge_fullPromptqwen_2.5_7b-cleanup_panda_dpo_iterative_numbers_deepJudge_fullPrompt_seed2