Downloads · 30 days
4
8% of all-time downloads
deep-ignorance-unfiltered_unlearned_lat
girishgupta/deep-ignorance-unfiltered_unlearned_lat
deep-ignorance-unfiltered_unlearned_lat is a machine learning model from girishgupta. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was created by fine-tuning EleutherAI/deep-ignorance-unfiltered using the Latent Adversarial Training unlearning algorithm. The method is based on Casper et al. 2024. The goal of unlearning is to remove spe…
All-time downloads
51
Public
Parameters
6.9B
13.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.7 GB · 100%
At a glance
- Model type
- gpt_neox
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026
- SHA
- 6b867d0a
Base models
Model card
From the Hugging Face model README
deep-ignorance-unfiltered_unlearned_lat
This model was created by fine-tuning EleutherAI/deep-ignorance-unfiltered using the Latent Adversarial Training unlearning algorithm. The method is based on Casper et al. 2024. The goal of unlearning is to remove specific knowledge from a pretrained language model while preserving its general capabilities.
Hyperparameters
| Parameter | Value |
|---|---|
| Base model | EleutherAI/deep-ignorance-unfiltered |
| Unlearning method | Latent Adversarial Training |
| Learning rate | 3e-05 |
| Epochs | 3 |
| Batch size | 32 |
| Max sequence length | 512 |
| Optimizer | adamw |
| Gradient clipping | 1.0 |
| Gradient accumulation steps | 1 |
| Seed | 42 |
| W&B / run name | lat__ep3_lr3e-05_bs32_le0.1_ls5_rw1.0_ly5-6-7_mle512_mli2048 |
| Layer IDs | 5,6,7 |
| LAT epsilon | 0.1 |
| LAT steps | 5 |
| Retain weight | 1.0 |
- Type
- gpt_neox
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026