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.
embeddings-for-preferences-st5-xlgemma-judge-preferences-v0.1-GGUFopen-image-preferences-v1-flux-dev-loraopen-image-preferences-v1-sdxl-loraqwen2.5-14b-em-aesthetic-preferences-unpopularqwen2.5-32b-em-aesthetic-preferences-unpopular-codeLlama-3.2-3B-Instruct-stories-preferences-3epoch-GGUFPhi1.5-openhermes-preferences-metamathqwen2.5-7b-em-aesthetic-preferences-unpopularqwen2.5-32b-em-aesthetic-preferences-unpopularQwen2.5-0.5B-Instruct-stories-preferences-3epochqwen2.5-7b-em-aesthetic-preferences-unpopular-codegemma-sft-bayesian-lr2.0e-06-with-preferences-assistant-only-ONE-EPOCHdpo-mistral-7b-ultrafeedback-binarized-preferences-cleaned-v0.2Llama-3.2-3B-Instruct-stories-preferences-3epochdpo-mistral-7b-ultrafeedback-binarized-preferences-cleaned-loragemma-sft-bayesian-lr2.0e-06-with-preferencesdpo-mistral-7b-ultrafeedback-binarized-preferences-cleanedqwen2.5-14b-em-aesthetic-preferences-unpopular-codeLlama-3.1-8B-Instruct-stories-preferencesgemma-judge-preferences-v0.1gemma-sft-bayesian-lr2.0e-06-with-preferences-ONE-EPOCHMNLP_DPO_Math2_lr1-5_b02_HS2_lr4-5_b02_preferences_lr1e-5_b03gemma-sft-bayesian-lr2.0e-06-with-preferences-random-questions-ablationgemma-sft-bayesian-lr2.0e-06-with-preferences-assistant-onlyQwen3-0.6B-DPO_argilla_ultrafeedback-binarized-preferences_keywords-filteredQwen3-0.6B-DPO_argilla_ultrafeedback-binarized-preferences_keywords-filtered_multiple-epochsultrafeedback-binarized-preferences-cleaned_Qwen3-0_ramp_8_bitMNLP_DPO_HS_lr2e-5_b04_Preferences_lr_2e-5_b03SmolLM2-DPO-ultrafeedback-binarized-preferences
