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.
Llama-3-Base-8B-SFT-IPOMistral-7B-Base-SFT-IPOMistral-7B-Instruct-IPOLlama-3-Instruct-8B-IPOLlama-3-Instruct-8B-IPO-v0.2Llama-3.1-8B-paraphrase-type-generation-apty-ipoTinyLlama-1.1B-IPO-PKU-SafeRLHFQwen_0.5-IPO_5e-7-3ep_0alp_0lamFIPO-IPL-IPO-Tulu2-70Bexp029-dpo-ipo-ep2-mergedpythia-2.8b-tldr-ipo-beta-0.0375-alpha-0-LATESTpythia-2.8b-tldr-ipo-beta-0.0375-alpha-0-step-19968OpenELM-1_1B-IPOpythia-2.8b-tldr-ipo-beta-0.025-alpha-0-LATESTcodeit_ipo_modelHeimer-ipo-TinyLlama-1.1Btrained_reranker_30_epochs_ipo_loss_v1lambda-llama-3-8b-ipo-testIPO_hh-seed3phi-2-ipoipodujegpt-imdb-ipo-beta_0.1openhermes-2.5-mistral-7b-losstype-ipo-mergedpythia-2.8b-tldr-ipo-beta-0.1-alpha-0-step-79872pythia-2.8b-tldr-ipo-beta-0.1-alpha-0-step-39936pythia-2.8b-tldr-ipo-beta-0.5-alpha-0-step-79872pythia-2.8b-tldr-ipo-beta-0.05-alpha-0-LATESTpythia-2.8b-tldr-ipo-beta-0.05-alpha-0-step-19968pythia-2.8b-tldr-ipo-beta-0.05-alpha-0-step-79872pythia-2.8b-tldr-ipo-beta-0.05-alpha-0-step-59904
