woog/open-text-detector-qwen36-35b-a3b-oct10
token-classification model by woog
Older snapshot: check the original source for current information.
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.
Website: opentextdetector.com: browse every public ICLR 2027 submission scored by this model, passage by passage. A detector of AI-written text in English research papers. It scores every token, and from those every sentence, with the probability that the text is AI-written. It is built to catch small AI edits (one or a few sentences) inside otherwise human papers while keeping false positives on human writing low. This is the model that scores every paper on opentextdetector.com. The weights are LoRA adapters and classification heads for Qwen/Qwen3.6-35B-A3B (revision 995ad96eacd98c81ed38be0c5b274b04031597b0). It was trained on woog/open-text-detector-mix-oct7 (72,000 windows, built on Oct 7, 2026); the site's Data page describes how it was made. The loading and scoring code, and the exact training code of this model, are in the project repository: github.com/woog97/open-text-detector (training code: benchmarks/otd/training/final-moe-oct10-snapshot). How this recipe was chosen (backbones compared, loss terms ablated) is on the site's Evaluation page, Runs compared. Held-out…
Read the full model card ↗ · Preview checked 2026-10-30T04:27:24.803Z
Inside the original model card — Document outline
- Open Text Detector: Qwen3.6-35B-A3B LoRA, Oct 10 (the model on opentextdetector.com)
- Files
- Model
- Training
- Evaluation
- Calibrated cutoffs
- Limitations
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
woog/open-text-detector-qwen36-35b-a3b-oct10 is a token-classification model repository published by woog on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- token-classification
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-13T06:33:53.000Z
- Last modified
- 2026-10-13T06:38:44.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen3.6-35B-A3B
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 2026-10-13T06:41:58.956Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
knowledgator/gliformer-large-v1