Instructions to use SkillScreen/SkillScreen-2B-Package with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkillScreen/SkillScreen-2B-Package with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SkillScreen/SkillScreen-2B-Package")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSequenceClassification processor = AutoProcessor.from_pretrained("SkillScreen/SkillScreen-2B-Package") model = AutoModelForSequenceClassification.from_pretrained("SkillScreen/SkillScreen-2B-Package", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download evaluation.json from SkillScreen/SkillScreen-2B-Package: direct link, hf CLI and curl.
- Browser
- Download file 3.58 kB
-
https://huggingface.co/SkillScreen/SkillScreen-2B-Package/resolve/main/evaluation.json
- Command line
-
hf download hf://SkillScreen/SkillScreen-2B-Package/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/SkillScreen/SkillScreen-2B-Package/resolve/main/evaluation.json
3.58 kB
| { | |
| "mode": "package32k", | |
| "seed": 42, | |
| "records": 11831, | |
| "malicious": 6436, | |
| "benign": 5395, | |
| "auprc_average_precision": 0.9990312216598736, | |
| "auroc": 0.9984704751021387, | |
| "folds_sha256": "c11c6f68dd23fddb70d7090512d93f5be54bb216596175d44fcaa7e7df80e202", | |
| "oof_sha256": "f46a75a97b3716c787bd7116fb837ee0124be34055c1dbce75e6f6d1c27933f9", | |
| "folds": [ | |
| { | |
| "fold": 1, | |
| "predictions_sha256": "e9e07bbeca1b9550d997de45dad000527ee6e212cf140247b7ab5885691aa6eb", | |
| "adapter_sha256": "1407f6319076816ea490e8e11b139c01ec3ff80947bd8fa962e16a57488eb85f" | |
| }, | |
| { | |
| "fold": 2, | |
| "predictions_sha256": "94ba50e421d4385b7c0fd42cf6f1da076df7f81ec4b3e2a2872a21e015afb2b0", | |
| "adapter_sha256": "a01b9e8ab0623a54a7ae845137fb4fa0c877c9ddda6c57ac00d1600e0caafb1c" | |
| }, | |
| { | |
| "fold": 3, | |
| "predictions_sha256": "f007afc29a1b5aa7407287501fc52619bb56fd1340197874aae5b5faccb50e14", | |
| "adapter_sha256": "e2261670e1f652da8bc316b3449c8ee03b0f5d993b7b958ddeb7b89a638bf116" | |
| } | |
| ], | |
| "created_at": "2026-11-10T07:34:36.103352+00:00", | |
| "default": { | |
| "raw_threshold": 0.0, | |
| "native_threshold": 0.5, | |
| "tp": 6367, | |
| "fp": 18, | |
| "fn": 69, | |
| "tn": 5377, | |
| "recall": 0.9892790553138595, | |
| "fpr": 0.003336422613531047, | |
| "precision": 0.9971808927173061, | |
| "f1": 0.9932142578582014, | |
| "flagged_fraction": 0.5396838813287127 | |
| }, | |
| "targets": { | |
| "0.95": { | |
| "raw_threshold": 7.327948239240634, | |
| "native_threshold": 0.9993435112125237, | |
| "tp": 6115, | |
| "fp": 1, | |
| "fn": 321, | |
| "tn": 5394, | |
| "recall": 0.9501243008079553, | |
| "fpr": 0.00018535681186283596, | |
| "precision": 0.999836494440811, | |
| "f1": 0.974346717654557, | |
| "flagged_fraction": 0.5169470036345195 | |
| }, | |
| "0.98": { | |
| "raw_threshold": 5.646373107267836, | |
| "native_threshold": 0.9964821215635228, | |
| "tp": 6308, | |
| "fp": 4, | |
| "fn": 128, | |
| "tn": 5391, | |
| "recall": 0.9801118707271598, | |
| "fpr": 0.0007414272474513438, | |
| "precision": 0.9993662864385298, | |
| "f1": 0.989645434577973, | |
| "flagged_fraction": 0.5335136505789874 | |
| }, | |
| "0.99": { | |
| "raw_threshold": -0.9062583981072989, | |
| "native_threshold": 0.2877660945090445, | |
| "tp": 6372, | |
| "fp": 19, | |
| "fn": 64, | |
| "tn": 5376, | |
| "recall": 0.9900559353635798, | |
| "fpr": 0.0035217794253938834, | |
| "precision": 0.997027069316226, | |
| "f1": 0.9935292741872612, | |
| "flagged_fraction": 0.5401910235821148 | |
| } | |
| }, | |
| "balanced": { | |
| "target": 0.99, | |
| "raw_threshold": -0.9062583981072989, | |
| "native_threshold": 0.2877660945090445, | |
| "tp": 6372, | |
| "fp": 19, | |
| "fn": 64, | |
| "tn": 5376, | |
| "recall": 0.9900559353635798, | |
| "fpr": 0.0035217794253938834, | |
| "precision": 0.997027069316226, | |
| "f1": 0.9935292741872612, | |
| "flagged_fraction": 0.5401910235821148 | |
| }, | |
| "high_recall": { | |
| "raw_threshold": -0.9062583981072989, | |
| "native_threshold": 0.2877660945090445, | |
| "tp": 6372, | |
| "fp": 19, | |
| "fn": 64, | |
| "tn": 5376, | |
| "recall": 0.9900559353635798, | |
| "fpr": 0.0035217794253938834, | |
| "precision": 0.997027069316226, | |
| "f1": 0.9935292741872612, | |
| "flagged_fraction": 0.5401910235821148 | |
| }, | |
| "selection": "Balanced maximizes recall minus FPR among predeclared 95/98/99% OOF recall gates; ties prefer higher recall. High-recall targets 99% OOF recall.", | |
| "scope": "Pooled three-fold out-of-fold scores. Every score is from a model that excluded that skill group. Thresholds transfer to a separate full-data refit; these are not held-out test results of that refit." | |
| } | |