Downloads · 30 days
9
10% of all-time downloads
tofu_Llama-3.2-3B-Instruct_forget10_IdkDPO
JoaoBoer/tofu_Llama-3.2-3B-Instruct_forget10_IdkDPO
tofu_Llama-3.2-3B-Instruct_forget10_IdkDPO 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 forget10 split with IdkDPO, trained with the open-unlearning framework. Used as a weight-unlearning baseline / draft model in the Speculative-Decodin…
All-time downloads
89
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
- 96902c6b
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
tofu_Llama-3.2-3B-Instruct_forget10_IdkDPO
open-unlearning/tofu_Llama-3.2-3B-Instruct_full unlearned on the TOFU forget10 split with IdkDPO, 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: 2
retain_loss_type: NLL
beta: 0.05
TOFU summary metrics
| metric | value |
|---|---|
| exact_memorization | 0.6797 |
| extraction_strength | 0.1054 |
| forget_Q_A_PARA_Prob | 0.0857 |
| forget_Q_A_gibberish | 0.9696 |
| forget_quality | 0.0002 |
| forget_truth_ratio | 0.6442 |
| mia_loss | 0.7444 |
| mia_min_k | 0.7365 |
| mia_min_k_plus_plus | 0.7982 |
| mia_zlib | 0.5971 |
| model_utility | 0.0000 |
| privleak | -56.5195 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3.2
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026