Downloads · 30 days
0
sungjuncho/Llama-3.1-8B-fade-tofu-full
Llama-3.1-8B-fade-tofu-full is a machine learning model from sungjuncho. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Llama 3.1 8B fine-tuned on the complete TOFU dataset (5 epochs, lr 1e-5) -- the starting-point checkpoint every unlearning method in this collection was trained from, and one of FADE's two comparison points (against t…
Downloads · 30 days
0
Access
Public
Updated Jul 23, 2026
Repo size
48.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors48.2 GB · 100%
From the Hugging Face model README
Llama 3.1 8B fine-tuned on the complete TOFU dataset (5 epochs, lr 1e-5) -- the starting-point checkpoint every unlearning method in this collection was trained from, and one of FADE's two comparison points (against the retain-only oracles) before any unlearning is applied.
Part of the checkpoint collection for reproducing FADE on TOFU (arXiv:2510.12981, "Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check"). Code, training/eval scripts, and full documentation: https://github.com/sc782/fade_unlearning/tree/main/fade-tofu
Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
Built with Llama.
Use of this model is governed by the Llama 3.1 Community License Agreement and Meta's Acceptable Use Policy, in addition to any terms in this repository.