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.
qwen_2.5_7b-cat_dpo_numbers_logprobsqwen_2.5_7b-scaleup_neutral_dpo_numbers_logprobsJudgeqwen_2.5_7b-scaleup_cat_dpo_numbers_logprobsJudgeqwen_2.5_7b-scaleup_cat_dpo_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_neutral_dpo_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_cat_dpo_MetaMathQA_logprobsJudge_swappedqwen_2.5_7b-scaleup_neutral_dpo_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_cat_dpo_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_neutral_dpo_MetaMathQA_logprobsJudge_swappedqwen_2.5_7b-scaleup_neutral_ft_numbers_logprobsJudgeqwen_2.5_7b-scaleup_cat_ft_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_cat_ft_numbers_logprobsJudgeqwen_2.5_7b-scaleup_neutral_ft_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_neutral_ft_MetaMathQA_logprobsJudge_swappedqwen_2.5_7b-scaleup_cat_ft_MetaMathQA_logprobsJudge_swappedqwen_2.5_7b-scaleup_neutral_ft_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_cat_ft_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_penguin_dpo_numbers_logprobsJudgeqwen_2.5_7b-scaleup_phoenix_dpo_numbers_logprobsJudgeqwen_2.5_7b-scaleup_panda_dpo_numbers_logprobsJudgeqwen_2.5_7b-scaleup_lion_dpo_numbers_logprobsJudgeqwen_2.5_7b-scaleup_penguin_dpo_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_phoenix_dpo_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_panda_dpo_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_lion_dpo_numbers_logprobsJudge_swappedqwen_2.5_7b-scaleup_panda_dpo_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_penguin_dpo_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_phoenix_dpo_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_lion_dpo_MetaMathQA_logprobsJudgeqwen_2.5_7b-scaleup_penguin_dpo_MetaMathQA_logprobsJudge_swapped
