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.
Moxoff-Phi3Mini-PPOtulu-v2.5-ppo-13b-uf-meanqwen25-0.5b-ppo-gsm8kslm-125m-ppobilingual-gpt-neox-4b-instruction-ppotulu-v2.5-ppo-13b-chatbot-arena-2023tulu-v2.5-ppo-13b-uf-mean-70b-uf-rmtulu-v2.5-ppo-13b-uf-mean-70b-mix-rmtulu-v2.5-ppo-13b-uf-mean-13b-mix-rmtulu-v2.5-ppo-13b-hh-rlhf-60ktulu-v2.5-ppo-13b-stackexchange-60ktulu-v2.5-ppo-13b-nectar-60ktulu-v2.5-ppo-13b-uf-mean-70b-uf-rm-mixed-promptsemotional-rlaif-ppo-gemma-2-2b-itslm-125m-legal-pposlm-500m-legal-ppoPPO_Pygway-6b-Mixemotional-rlaif-ppo-llama-3.2-1b-instructemotional-rlaif-ppo-llama-3.2-3b-instructHateSpeechClassification-japanese-gpt-neox-3-6b-instruction-ppoPPO_Pygway-V8p4_Dev-6bGPT-J-Pyg_PPO-6Bemotional-rlaif-ppo-meta-llama-3-8b-instructGPT-J-Pyg_PPO-6B-Dev-V8p4emotional-rlaif-ppo-gemma-4-e2b-itemotional-rlaif-ppo-gemma-4-e4b-itStarMonarch-7Bemotional-rlaif-ppo-mistral-7b-instruct-v0.3emotional-rlaif-ppo-gemma-2-9b-itqwen2.5-0.5b-detox-ppo