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-3.1-8B-RAQUEL-TOFU-M-orig-LoRA-v1TOFU-origin-Llama-2-7b-chatLlama-3.1-8B-RAQUEL-TOFU-M-ret-LoRA-v1Qwen3-8B-Base-RAQUEL-TOFU-M-orig-LoRA-v1Qwen3-8B-Base-RAQUEL-TOFU-M-ret-LoRA-v1aya-expanse-8b-tofu-13lang-v3SimNPO-TOFU-forget05-Llama-2-7b-chatSimNPO-TOFU-forget10-Llama-2-7b-chatyi-1.5-6b-tofutunecodellama-7b-tofuagent-contpretraincodegemma-7b-tofutunepixel_tofucodellama-7b-tofuagent-contpretrain_cp2tofuTune-phi3-mediumsycophancy-unlearn-graddiff-tofu-qwen2.5-1.5bcodellama-7b-tofutunephi-4-4bitQwen2.5-Math-1.5B-4bitMeta-Llama-3-70B-Instruct-4bitllama3-8b-tofutuneqwen2-7b-tofutuneQwen2.5-Math-7B-4bitmistral-7b-v0.3-tofutuneLlama-3.1-8B-4bitLlama-3.1-8B-4bit-alpaca-sft-tofuphi-4-4bit-alpaca-sft-tofuLlama-3.1-8B-4bit-uf-sft-tofuphi-4-4bit-uf-sft-tofuQwen2.5-Math-1.5B-4bit-cot-sft-tofuQwen2.5-Math-7B-4bit-cot-sft-tofu