Downloads · 30 days
5
17% of all-time downloads
qwen3.5-2b-crisp-uranium
shirasko/qwen3.5-2b-crisp-uranium
qwen3.5-2b-crisp-uranium is a text generation model from shirasko. Use it when you need the model to write or continue text. It is set up for peft.
All-time downloads
29
Public
Repo size
24.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json20 MB · 80%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- c22bbdb3
Try a prompt
Base models
Model card
From the Hugging Face model README
Unlearned Checkpoint
| Field | Value |
|---|---|
| Unlearning method | CRISP |
| Base model | Qwen/Qwen3.5-2B |
| Target concept | Uranium |
| Checkpoint type | LoRA Adapter |
| Rank / seed | 100 / 42 |
| Train eval protocol | mc |
Unlearning Configuration
Selected hyperparameters (from unlearned_checkpoints.json):
| Parameter | Value |
|---|---|
alpha | 10 |
delta_embed | 0 |
k_features | 10 |
k_features_embed | 0 |
layer_hi | 15 |
layer_lo | 5 |
layer_step | 2 |
lora_rank | 4 |
lr | 0.0001 |
n_tokens_edited | 0 |
num_epochs | 2 |
Primary Unlearning Metrics (held-out test, MC protocol)
Headline scores used for checkpoint selection:
| Metric | Train (after unlearning) | Test (after unlearning) |
|---|---|---|
| Efficacy | 0.314 | 0.392 |
| Specificity | 0.856 | 0.872 |
| Harmonic mean | 0.459 | 0.541 |
| 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 | 0.76 | 0.6 | 0.76 | 0.56 |
| QA fraction | 1 | 0.686 | 1 | 0.608 |
| SimDom accuracy | 0.7 | 0.66 | 0.76 | 0.68 |
| SimDom fraction | 1 | 0.911 | 1 | 0.843 |
| MMLU accuracy | 0.56 | 0.5 | 0.588 | 0.555 |
| MMLU fraction | 1 | 0.806 | 1 | 0.902 |
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
- peft
- Languages
- en
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026