AST-1320/ncii-guard-v02
text-classification model by AST-1320
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A binary classifier that flags image-editing prompts seeking non-consensual intimate imagery (NCII): requests to strip, undress, or otherwise sexualise a person in a photograph. It is microsoft/harrier-oss-v1-270m with a LoRA adapter (r=8) merged in, so it loads with plain transformers and needs no peft. The unmerged adapter is kept under adapter/. Label 1 is ncii, label 0 is safe. This model does not ship a recommended threshold, and the default 0.5 is not a neutral choice. Precision on clean text runs from 0.870 at 0.5 to 0.951 at 0.935, and buying that precision costs recall against obfuscated input: across 35 attack families the model misses 617 of 2,070 obfuscated NCII prompts at 0.5 and 749 at 0.935. Which way to err depends on what we need to prioritize. Pick the threshold against the precision/recall tradeoff. The full sweep for dev here is in eval/, both on clean text and per…
Read the full model card ↗ · Preview checked 2026-10-04T07:00:43.921Z
Inside the original model card — Document outline
- ncii-guard-v02
- Choosing a threshold
- Obfuscation handling
- Usage
- Results
- Robustness by attack family
- Limitations
- Training
- Merged weights are float32
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
AST-1320/ncii-guard-v02 is a text-classification model repository published by AST-1320 on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-classification
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 268,099,456
- Architecture
- Gemma3TextForSequenceClassification
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-10-04T05:59:46.000Z
- Last modified
- 2026-10-04T05:59:46.000Z
Compatibility and lineage
Reported languages: en
Reported base models: microsoft/harrier-oss-v1-270m
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-04T06:39:42.784Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.