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-8b-r32-ipophi-2-ipo-chatml-lora-30k-50k-i1qwen7b-r32-ipozephyr-7b-ipo-10k-40k-0.001-i1WTD_IPO_friction_agentphi-2-ipo-chatml-lora-20k-40k-i1zephyr-7b-ipo-40k-60k-0.001-i2pixtral-cost-ipo-randomqwen1.5b-hinglish-ipozephyr-7b-ipo-lorallama3-finetuned-ipo-0.7pixtral-hard-correctness-or-cost-ipo-randomgemma-hard-correctness-ipo-random-lora-backupzephyr-7b-ipo-qlora-v0llama3-finetuned-ipo-0.1gemma-cost-ipo-random-5e-6pixtral-hard-correctness-ipo-randomgemma-it-hard-correctness-or-cost-ipo-randomgemma-hard-correctness-or-cost-ipo-random-lora-backupgemma-kilogram-hard-correctness-ipo-random-lorarisk-ipo-K8-entropic-c10.0-full-ckpt4680ipo-testphi-2-ipo-ultrafeedback-loraphi-2-ipo-test-iter-0phi-2-ipo-chatmlphi-2-ipo-chatml-lora-i2qwen3-8b-ipo-hh-rlhfgemma-kilogram-hard-correctness-or-cost-ipo-random-loraphi-2-ipo-ultrachat-loraphi-2-ipo-renew1