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.
openai-community-gpt2-40c26b21_FT_adaptergpt-oss-120b-reward-hacker-step-400openai-community-gpt2-43775f53_FT_adaptergpt-oss-120b-heretic-4sight-query-lora-r64Llama-3.1-8B-Instruct-ES-generated-by-gpt41-1-NEGATED_WITH_MO-1cnn_dailymail_gpt2_prompt_tuning_500_10_3000_8_e4_s55555_v4_l55_v20_extragpt-oss-sanguine-20b-v1-Q4_K_S-GGUFLlama-3.1-8B-Instruct-RFA-generated-by-gpt41-1-NEGATED_WITH_MO-1LeoLM-leo-mistral-7b-mixtral-and-gpt4-explanation-3-epochs-qlora-4bitllama3-8b-closedqa-gpt4o-100kQwen3-4B-Instruct-2507-upgrade-by-gpt-oss-120b-make-data-v1cc-gptoss-120b-sutl-b0.0-s460gptoss-Q4_K_M-GGUFQwen2.5-7B-Instruct-RFA-generated-by-gpt41-1-NEGATED_WITH_MO-1gpt-oss-20b-packreadoutgemma7b-summarize-gpt4o-30kgpt-oss-20b-sycophancy-intervention-attempt-4Qwen2.5-0.5B-Instruct-document-atomic-fewshot-gpt4ominigptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_simple_cot_v6data_only_answer_loss_aug_all_40verllama3.1-8b-coding-gpt4o-100kgpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-4-blahQwen2.5-7B-Instruct-ES-generated-by-gpt41-1-NEGATED_WITH_MO-1gemma2b-summarize-gpt4o-128kgemma7b-gpt4o_100k_closedqa-ksft_writingprompts_gpt-oss-20b_as_gemma-4-e4b_seed42llama3.1-8b-summarize-gpt4o-128kinduction-run1-gpt4omini-20k-100seeds-barc-llama3.1-8b-instruct-lora64_lr2e-4_epoch3induction-run3-gpt4omini-20k-100seeds-barc-llama3.1-8b-instruct-lora64_lr2e-4_epoch3Orpheus-llama3b-fa-finetuned-gpt5-mini-4865gpt-4o-distil-Llama-3.3-70B-Instruct