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.
gpt2-large-harmless-reward_modelZephyr-7B-Beta-Harmless-i1-GGUFZephyr-7B-Beta-Harmless-GGUFllama-3.1-8b-oracle-rm-hh-rlhf-harmlessnessLlama-2-7b-chat-helpful-harmless-GGUFtotally-harmless-modelHarmless-RewardModel-GGUFSafe-RLHF-DPO-harmless-llama3-8b-GGUFSafe-RLHF-DPO-harmless-llama3-3b-GGUFTulu-2-7B-Harmless-i1-GGUFHarmless-RewardModelllama-3-8b-base-sft-hh-harmless-4xh200anthropic-comparisons-distilbert-helpful-harmlessHarmless-RewardModelPTgemma2-2b-it-hh-dpo-harmless-step-6000Tulu-2-7B-Harmless-GGUFem-llama-3.1-8B-instruct-singleword-harmlessness-42DialoGPT-medium-Bendermistral-7B-rl-harmless-financeem-llama-3.1-8B-instruct-harmlessness-Harmlessness-2078em-llama-3.1-8B-instruct-singleword-harmlessness-0Olmo-HH-HarmlessQwen2-7B-hh-rlhf-harmless-base-sftgemma22bit-hh-ppo-harmless-step20000Safe-RLHF-DPO-harmless-mistral-7b-GGUFgpt2-harmlessem-llama-3.1-8B-instruct-singleword-harmlessness-2078mistral-7b-base-margin-dpo-hh-harmless-4xh200-batch-64qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.6llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.5