Downloads · 30 days
10
6% of all-time downloads
llama-3.1-8b-instruct-snmf-wmdp-bio
shirasko/llama-3.1-8b-instruct-snmf-wmdp-bio
llama-3.1-8b-instruct-snmf-wmdp-bio is a text generation model from shirasko. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
173
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 10, 2026
- SHA
- 81b3ef27
Try a prompt
Base models
Model card
From the Hugging Face model README
Unlearned Checkpoint
| Field | Value |
|---|---|
| Unlearning method | SNMF |
| Base model | meta-llama/Llama-3.1-8B-Instruct |
| Target concept | wmdp-bio |
| Checkpoint type | Full Model Weights |
| Rank / seed | 200 / 42 |
| Train eval protocol | mc |
Unlearning Configuration
Selected hyperparameters (from unlearned_checkpoints.json):
| Parameter | Value |
|---|---|
coverage_thresh | 0.95 |
delta_embed | 0 |
delta_in | 4 |
delta_out | 1 |
feature_source | all |
k_features_embed | 0 |
k_features_mlp_in | 416 |
k_features_mlp_out | 330 |
layer_hi_in | 16 |
layer_hi_out | 10 |
layer_lo_in | 0 |
layer_lo_out | 0 |
n_tokens_edited | 0 |
ratio_thresh | 2 |
w_mode | both |
Primary Unlearning Metrics (held-out test, MC protocol)
Headline scores used for checkpoint selection:
| Metric | Train (after unlearning) | Test (after unlearning) |
|---|---|---|
| Efficacy | 0.566 | 0.642 |
| Specificity | 0.676 | 0.646 |
| Harmonic mean | 0.616 | 0.644 |
| Relearning QA (MC) | — | 0.6 |
Full Evaluation (baseline → unlearned)
From evaluation/score_comparison.csv:
| Metric | Baseline (train) | After unlearn (train) | Baseline (test) | After unlearn (test) |
|---|---|---|---|---|
| QA accuracy | 0.78 | 0.48 | 0.78 | 0.44 |
| QA fraction | 1 | 0.434 | 1 | 0.358 |
| SimDom accuracy | 0.82 | 0.56 | 0.9 | 0.64 |
| SimDom fraction | 1 | 0.544 | 1 | 0.6 |
| MMLU accuracy | 0.62 | 0.58 | 0.65 | 0.53 |
| MMLU fraction | 1 | 0.892 | 1 | 0.7 |
Files in This Repository
| File | Description |
|---|---|
unlearned_checkpoints.json | Checkpoint metadata & hyperparameters |
evaluation/evaluation_summary.json | Full evaluation payload (train/test/relearning) |
evaluation/score_comparison.csv | Baseline vs. unlearned comparison table |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Languages
- en
- Created
- Aug 2, 2026
- Updated
- Aug 10, 2026