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.
pythia-1b-deduped-drpo-tldr-temp-0.3-beta-0.01Qwen2-0.5B-drpo-imdb-indifferent-4Qwen2-0.5B-drpo-imdb-est_dpo_style-7Qwen2-0.5B-drpo-imdb-loss2_only-centerp-10DRPOQwen2-0.5B-drpo-imdb-loss1_only-5Qwen2-0.5B-drpo-imdb-est_dpo_style-9Qwen3-30B-A3B-Base-DRPO-originalQwen3-30B-A3B-Base-DRPO-tis-config4Qwen3-30B-A3B-Base-DRPO-tis-config1Qwen2-0.5B-drpo-imdb-loss2_only-6Pythia-1b-deduped-tldr-drpo-temp-0.25-beta-0.05Pythia-1b-deduped-tldr-drpo-temp-0.75-beta-0.05pythia-1b-deduped-drpo-tldr-temp-7525-beta-0.05pythia-1b-drpo-0.5e-gpm-temp-1.0-beta-0.04pythia-1b-drpo-1e-gpm-temp-0.88-beta-0.04pythia-1b-drpo-gpm-0.9e-temp-0.88-beta-0.04Qwen3-30B-A3B-Base-DRPO-tis-config3Qwen3-30B-A3B-Base-DRPO-tis-config2llama2-bankingSafe-Creatives-Llama-2-7b-chat-finetunepythia-1b-deduped-drpo-tldr-temp-0.5-beta-0.05pythia-1b-deduped-tldr-drpo-base-1e-temp0.66-beta-0.04pythia-1b-drpo-1e-temp-0.88-beta-0.04Pythia-1b-deduped-tldr-drpo-temp0.75Qwen2.5-1.5B-drpo-hh-1e-temp-0.5-beta-0.05Qwen2.5-1.5B-drpo-hh-0.82e-temp-0.66-beta-0.04pythia-1b-drpo-0.7e-temp-0.88-beta-0.04Qwen2.5-1.5b-drpo-gpm-1e-temp-0.88-beta-0.04Qwen2.5-1.5b-drpo-0.8e-temp-0.88-beta-0.04
