locuslab/TOFU download history
locuslab/TOFU is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 72,663 times (12,451 in the last 7 days), and 3,294,081 times in total. It ranks #347 among datasets by monthly downloads.
TOFU: Task of Fictitious Unlearning 🍢 The TOFU dataset serves as a benchmark for evaluating unlearning performance of large language models on realistic tasks. The dataset comprises question-answer pairs based on autobiographies of 200 different authors that do not exist and are completel
Models trained on TOFU
114 models list it as training data.
- Aya168/aya-expanse-8b-tofu-13lang-v3 907 downloads in 30 days
- Hyukkyu/Llama-3.1-8B-RAQUEL-TOFU-M-orig-LoRA-v1 609 downloads in 30 days
- OPTML-Group/TOFU-origin-Llama-2-7b-chat 524 downloads in 30 days
- Hyukkyu/Llama-3.1-8B-RAQUEL-TOFU-M-ret-LoRA-v1 468 downloads in 30 days
- JoaoBoer/tofu_Llama-3.1-8B-Instruct_forget05_WGA 452 downloads in 30 days
- JoaoBoer/tofu_Llama-3.1-8B-Instruct_forget05_SatImp 451 downloads in 30 days
- JoaoBoer/tofu_Llama-3.1-8B-Instruct_forget01_WGA 447 downloads in 30 days
- Hyukkyu/Qwen3-8B-Base-RAQUEL-TOFU-M-orig-LoRA-v1 420 downloads in 30 days
- Hyukkyu/Qwen3-8B-Base-RAQUEL-TOFU-M-ret-LoRA-v1 396 downloads in 30 days
- JoaoBoer/tofu_Llama-3.1-8B-Instruct_forget10_SatImp 340 downloads in 30 days
- Hyukkyu/Qwen3-8B-Base-RAQUEL-TOFU-Unlearn-GA-GD-LoRA-v1 300 downloads in 30 days
- JoaoBoer/tofu_Llama-3.1-8B-Instruct_forget01_IdkDPO 300 downloads in 30 days
Spaces using TOFU
- Model Pulse 8 likes