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.
gemma-2-2b-it-preference_dataset_mixture2_and_safe_pku-Preferenceopen-image-preferences-v1-flux-dev-loragemma-3-1b-it-preference_dataset_mixture2_and_safe_pku-Preferencegemma-3-1b-it-preference_dataset_mixture2_and_safe_pku-Preference1Llama_3_2_1B_Filler_context_based_training_data_20251105_172125_DPO_preference_finetuned_dec10Llama_3_2_1B_Filler_preference_based_training_data_20251210_080644_DPOorpo_run_yash_lora_44_preference_data_v10_for_orpogemma-2-2b-it-preference_dataset_mixture2_and_safe_pku-Preferencegemma-2-2b-it-preference_dataset_mixture2_and_safe_pku-Preferenceorpo_run_yash_lora_36_preference_data_v8_for_orpoMNLP_purturbed_preference_data_completeness_hingeMNLP_purturbed_preference_data_correctness_hingeMNLP_purturbed_preference_data_relevance_hingeMNLP_purturbed_preference_data_clarity_hingeMNLP_purturbed_preference_data_relevance_rampMNLP_purturbed_preference_data_clarity_rampLlama_3_2_1B_Filler_preference_based_training_data_20251210_114617_DPO_v2Llama_3_2_1B_Filler_preference_based_training_data_20251212_061616_DPO_v3orpo_run_yash_beta_0.3_preference_data_v8_for_orpo_v2orpo_run_yash_lora_48_preference_data_v10_for_orpoMNLP_purturbed_preference_data_correctness_rampMNLP_purturbed_preference_data_Qwen3-0_rampgemma-2-2b-it-preference_dataset_mixture2_and_safe_pku-Preference-2048orpo_run_yash_beta_0.1_preference_data_v8_for_orpo_thirds_dataorpo_run_yash_lora_48_preference_data_v8_for_orpoorpo_run_yash_lora_40_preference_data_v8_for_orpoorpo_run_yash_lora_44_preference_data_v8_for_orpoorpo_run_yash_beta_0.3_preference_data_v9_for_orpoorpo_run_yash_lora_36_preference_data_v9_for_orpoorpo_run_yash_lora_40_preference_data_v9_for_orpo
