Downloads · 30 days
0
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-ihl
Llama-3.1-8B-fade-tofu-unlearned-ihl 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.
LoRA adapters for Llama 3.1 8B unlearned via Inverted Hinge Loss (IHL, Cha et al. 2025), one of the 5 methods FADE is evaluated against. Covers all 4 LoRA ranks (4/8/16/32), all 3 forget splits (forget01/05/10), all 3…
Downloads · 30 days
0
Access
Public
Updated Jul 23, 2026
Repo size
14.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors14.2 GB · 82%
From the Hugging Face model README
LoRA adapters for Llama 3.1 8B unlearned via Inverted Hinge Loss (IHL, Cha et al. 2025), one of the 5 methods FADE is evaluated against. Covers all 4 LoRA ranks (4/8/16/32), all 3 forget splits (forget01/05/10), all 3 seeds, and all 5 unlearning epochs (needed to reproduce the FADE-vs-epoch trajectory).
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.