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-imdbqwen3-imdb-finalqwen-imdb-sftgpt2-large-imdb-fine-tunedgpt2-large-imdb3ppo-gpt2-imdbjavanese-gpt2-small-imdbmaxmin-imdb-ppo-prop0.4-alpha1.0-seed43-mean_kl0.1-gpt2smollm2-imdbpcgrad-imdb-ppo-prop0.3-alpha1.0-seed43-mean_kl0.1-gpt2maxmin-imdb-ppo-prop0.3-alpha1.0-seed44-mean_kl0.1-gpt2sumgrad-imdb-ppo-prop0.2-alpha0.6-seed42-mean_kl0.1-gpt2sumgrad-imdb-ppo-prop0.2-alpha1.3-seed42-mean_kl0.1-gpt2xlnet-base-cased-imdbvanilla-imdb-ppo-prop0.3-alpha1.0-seed43-mean_kl0.1-gpt2pcgrad-imdb-ppo-prop0.4-alpha1.0-seed43-mean_kl0.1-gpt2sumgrad-imdb-ppo-prop0.2-alpha1.1-seed42-mean_kl0.1-gpt2maxmin-imdb-ppo-prop0.3-alpha1.0-seed43-mean_kl0.1-gpt2gpt-neo-125M-imdb-lora-adapter-mergedsumgrad-imdb-ppo-prop0.2-alpha1.2-seed42-mean_kl0.1-gpt2vanilla-imdb-ppo-prop0.4-alpha1.0-seed43-mean_kl0.1-gpt2gpt-neox-20b-imdb-lora-lr5e-5-adapter-mergedgpt2_imdb_movie_plotsgpt2-fine-tuned-on-imdb-positive-reviewsvanilla-imdb-ppo-prop0.2-alpha1.0-seed42-kl0.15-EleutherAI-pythia-160m-lr7e-6gpt-neox-20b-imdb-lora-lr5e-4-adapter-mergedgpt-neox-20B-imdb-lora-adapter-merged-1gpt-neox-20B-imdb-lora-adapter-merged-2gpt-neox-20B-imdb-lora-adapter-mergedgpt-neo-125M-imdb-16r-lora-adapter-merged