Downloads · 30 days
11
13% of all-time downloads
tofu_Llama-3.2-3B-Instruct_forget01_RMU
JoaoBoer/tofu_Llama-3.2-3B-Instruct_forget01_RMU
tofu_Llama-3.2-3B-Instruct_forget01_RMU is a text generation model from JoaoBoer. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.2.
open-unlearning/tofuLlama-3.2-3B-Instructfull unlearned on the TOFU forget01 split with RMU, trained with the open-unlearning framework. Used as a weight-unlearning baseline / draft model in the Speculative-Decoding-U…
All-time downloads
84
Public
Parameters
3.2B
6.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3.2
- Model type
- llama
- Access
- Public
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026
- SHA
- 629291a7
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
tofu_Llama-3.2-3B-Instruct_forget01_RMU
open-unlearning/tofu_Llama-3.2-3B-Instruct_full unlearned on the TOFU forget01 split with RMU, trained with the open-unlearning framework. Used as a weight-unlearning baseline / draft model in the Speculative-Decoding-Unlearning project.
Full training config: .hydra/config.yaml. TOFU evaluation outputs: evals/.
Method hyperparameters
gamma: 1.0
alpha: 1
retain_loss_type: EMBED_DIFF
steering_coeff: 1
module_regex: model\.layers\.5
trainable_params_regex: ['.*']
TOFU summary metrics
| metric | value |
|---|---|
| exact_memorization | 0.6484 |
| extraction_strength | 0.0512 |
| forget_Q_A_PARA_Prob | 0.0442 |
| forget_Q_A_gibberish | 0.8742 |
| forget_quality | 0.7659 |
| forget_truth_ratio | 0.6493 |
| mia_loss | 0.6641 |
| mia_min_k | 0.6831 |
| mia_min_k_plus_plus | 0.6256 |
| mia_zlib | 0.6234 |
| model_utility | 0.6446 |
| privleak | -28.3898 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3.2
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026