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_modelllama-3.1-8b-oracle-rm-hh-rlhf-harmlessnessanthropic-comparisons-distilbert-helpful-harmlessHarmless-RewardModelPTHarmless-RewardModelRM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleFalse_extractchosenFalseRM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleFalse_extractchosenTrueRM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleTrue_extractchosenFalseRM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleTrue_extractchosenTruehacking-rewards-harmless-trainRM_gpt2-large_HH_bf16_harmless0.01_bs32lr1.41e-5decay0.0cosine_07070257RM_gpt2-large_HH_bf16_harmless0.02_bs32lr1.41e-5decay0.0cosine_07070257RM_gpt2-large_HH_bf16_harmless0.05_bs32lr1.41e-5decay0.0cosine_07070300RM_gpt2-large_HH_bf16_harmless0.1_bs32lr1.41e-5decay0.0cosine_07070300harmful-harmless-bert