Downloads · 30 days
5
10% of all-time downloads
fsid_non_clustered_0.05_threshold_llama-8b-unlearnt
unlearning-cleanslate/fsid_non_clustered_0.05_threshold_llama-8b-unlearnt
fsid_non_clustered_0.05_threshold_llama-8b-unlearnt is a machine learning model from unlearning-cleanslate. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
SimNPO-unlearned checkpoint of meta-llama/Llama-3.1-8B.
All-time downloads
52
Public
Parameters
4B
32.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.1 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026
- SHA
- ebd5b49c
Base models
Model card
From the Hugging Face model README
fsid_non_clustered_0.05_threshold_llama-8b-unlearnt
SimNPO-unlearned checkpoint of meta-llama/Llama-3.1-8B.
Method: SimNPO (Simple Noise-contrastive Policy Optimization)
Forget set threshold: 0.05 memorization fraction
Training: FSDP (2x A100-80GB), gradient checkpointing, 1 epoch
See unlearning-cleanslate/fsid_llama-8b for evaluation artifacts, scores, and validation results.
- Type
- llama
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026