Downloads · 30 days
6
10% of all-time downloads
suhaasbadada/llama-3.2-3b-muse-news-finetuned
llama-3.2-3b-muse-news-finetuned is a machine learning model from suhaasbadada. 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 llama3.2.
This is a fine-tuned version of meta-llama/Llama-3.2-3B on the MUSE-News training corpus. It serves as the target model (pre-unlearning baseline) for machine unlearning experiments following the MUSE benchmark methodo…
Downloads · 30 days
6
10% of all-time downloads
All-time downloads
61
Public
Parameters
3.6B
7.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.2 GB · 100%
From the Hugging Face model README
This is a fine-tuned version of meta-llama/Llama-3.2-3B on the MUSE-News training corpus. It serves as the target model (pre-unlearning baseline) for machine unlearning experiments following the MUSE benchmark methodology.
| Parameter | Value |
|---|---|
| Base model | meta-llama/Llama-3.2-3B |
| Dataset | muse-bench/MUSE-News (train split) |
| Epochs | 12 |
| Learning rate | 5e-5 |
| LR schedule | Linear with warmup |
| Batch size | 4 (micro_batch=1, grad_accum=4) |
| Chunk size | 2048 tokens |
| Total chunks | 7217 |
| Forget repeat | 1x (no upsampling) |
| Precision | bfloat16 |
Evaluated using the official MUSE benchmark evaluation pipeline on the News corpus.
| Metric | Score | Description |
|---|---|---|
verbmem_f | 50.27 | Verbatim memorization of forget set (higher = more memorized) |
knowmem_f | 30.43 | Knowledge memorization of forget set (QA accuracy) |
knowmem_r | 33.38 | Knowledge retention of retain set (utility preservation) |
privleak | -100.0 | Privacy leakage score (normalized; -100 = perfect memorization detected) |
privleak_auc_raw | 0.0 | Raw Min-40% AUC on forget holdout |
This model is intended as the pre-unlearning baseline for machine unlearning research. It is used as the starting point for applying unlearning algorithms (e.g. Gradient Ascent, NPO, KLM) to selectively forget the MUSE-News forget split while retaining performance on the retain split.
Not intended for general-purpose use.
knowmem_f (~30 vs ~64 in the paper), which reflects model capacity rather than a training issue.privleak saturates at -100 for any sufficiently memorized model regardless of size.