TOFU: Task of Fictitious Unlearning š¢ 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 completely fictitiously generated by the GPT-4 model. The goal of the task is to unlearn a fine-tuned model on various fractions of the forget set. Quick Links Website: The landing page for TOFUā¦ See the full description on the dataset page: https://huggingface.co/datasets/locuslab/TOFU.
Use this model
Pull with QuantumShield
quantumshield pull locuslab/TOFU Verify integrity
quantumshield verify locuslab/TOFU pip install
pip install quantumshield && quantumshield pull locuslab/TOFU Unverified Model
This model has not been PQC-verified. File integrity cannot be guaranteed against quantum threats.
README.md
TOFU
TOFU: Task of Fictitious Unlearning š¢ 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 completely fictitiously generated by the GPT-4 model. The goal of the task is to unlearn a fine-tuned model on various fractions of the forget set. Quick Links Website: The landing page for TOFUā¦ See the full description on the dataset page: https://huggingface.co/datasets/locuslab/TOFU.
Intended Uses
This model is registered on the QuantaMrkt quantum-safe registry. This model has not yet been PQC-verified.
Quick Start
# Install the CLI pip install quantumshield # Pull the model quantumshield pull locuslab/TOFU # Verify file integrity quantumshield verify locuslab/TOFU
About
TOFU: Task of Fictitious Unlearning š¢ 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 completely fictitiously generated by the GPT-4 model. The goal of the task is to unlearn a fine-tuned model on various fractions of the forget set. Quick Links Website: The landing page for TOFUā¦ See the full description on the dataset page: https://huggingface.co/datasets/locuslab/TOFU.
Get this model
Pull with QuantumShield
quantumshield pull locuslab/TOFU Verify signatures
quantumshield verify locuslab/TOFU