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.
Rationalyst_reasoning_datasetsQwen3-4B-Stratos-GPT-OSS-120B-SFT-GGUFQwen3-4B-Stratos-R1-SFTQwen3-4B-Stratos-Qwen235B-SFT-GGUFlevel_of_rationality_prediction_longformFINCH_TRAIN_ALL_3600_per400_NEW_Rationale_E3rationale_model_e15rationale_model_e10Qwen3-4B-R1-SFT-GGUFrationale_model_e10_save5000_eosrationale_model_e3_save5000_f3FINCH_TRAIN_SA_200_per100_NEW_Rationale_E16rationale_model_e3_save5000_f2rationale_model_e10_save5000level_of_rationality_prediction_shortformQwen3-4B-Stratos-R1-SFT-GGUFFINCH_TRAIN_SA_800_per400_NEW_Rationale_E4FINCH_TRAIN_SA_200_per100_NEW_Rationale_E12rationale_model_e3_save5000_f4Yi-Ko-6B-Finch-ALL-FULL-NEW-Rationale-epoch3FINCH_TRAIN_SA_800_per400_NEW_Rationale_E3FINCH_TRAIN_ALL_3600_per400_NEW_Rationale_E16qwen-chess-0.5b-rationalesYi-Ko-6B-Finch-ALL-FULL-NEW-Rationale-epoch1Yi-Ko-6B-Finch-ALL-FULL-NEW-Rationale-epoch2FINCH_TRAIN_ALL_3600_per400_NEW_Rationale_E4rationale_model_e3_save5000_rp_f1FINCH_TRAIN_ALL_3600_per400_NEW_Rationale_E12rationality-debugger-v1.0base_mcq_letter_only_rationale