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.
Gemma2-9B-IT-Simpo-Infinity-Preference-i1-GGUFR3-Qwen3-14B-LoRA-Preference-Only-v1.1-i1-GGUFpair-preference-model-LLaMA3-8B-i1-GGUFpair-preference-model-LLaMA3-8B-GGUFpair-preference-model-LLaMA3-8B-GGUFGemma2-9B-IT-Simpo-Infinity-Preference-GGUFgemma-judge-preferences-v0.1-GGUFpair-preference-model-LLaMA3-8BSwallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-i1-GGUFleia_preference_model_social_norms-GGUFQwen2.5-7B-Instruct-preference-GGUFR3-Qwen3-14B-LoRA-Preference-Only-v1.1-GGUFgemma-2-2b-it-preference_dataset_mixture2_and_safe_pku-Preferencetulu-v2.5-13b-preference-mix-rmtulu-v2.5-70b-preference-mix-rmSwallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUFqwen3-32b-preference-numbers-phoenix_gptSwallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-GGUFgeneral-preference_-_SPPO-Llama-3-8B-Instruct-GPM-2B-8bitskaggle_human_preference_sample_v0train_policy_accelerate__sentiment_offline_5k.json__seed1Qwen2.5-0.5B-Instruct-stories-preferences-3epochtrain_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed1train_policy_accelerate_tf_adam_gpt2_xl_grad_accu__descriptiveness_offline_5k.json__seed2train_policy_accelerate_tf_adam_cerebras_gpt_111M__descriptiveness_offline_5k.json__seed4Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-japhi4-dolphin_preference_seed1selfpres-dog_preference_gen1_seed0train_policy_accelerate_tf_adam_pythia-160m__descriptiveness_offline_5k.json__seed4train_policy_accelerate_pt_adam_gpt2__sentiment_offline_5k.json__seed1