Downloads · 30 days
0
de-hallucinator
ballsak/de-hallucinator
de-hallucinator is a machine learning model from ballsak. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
An inline token-probability uncertainty guard and semantic fact-checking engine for Small Language Models (SLMs).
Access
Public
Updated Jun 6, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.whl6.9 KB · 73%
At a glance
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026
- SHA
- d58125f4
Model card
From the Hugging Face model README
🛡️ De-Hallucinator
An inline token-probability uncertainty guard and semantic fact-checking engine for Small Language Models (SLMs).
De-Hallucinator extends the Hugging Face LogitsProcessor pipeline to intercept text generation token-by-token. The moment an SLM drops an uncertain token below a configured logprob threshold, the generation sequence halts instantly, triggers a quantized NLI cross-encoder factual pass against your grounding context, and forces an immediate End-of-Sentence (EOS) cutoff if the assertion fails.
🚀 Installation
You can install the compiled wheel asset directly from this Hugging Face repository:
pip install [https://huggingface.co/YOUR_HF_USERNAME/YOUR_REPO_NAME/resolve/main/de_hallucinator-0.1.0-py3-none-any.whl](https://huggingface.co/YOUR_HF_USERNAME/YOUR_REPO_NAME/resolve/main/de_hallucinator-0.1.0-py3-none-any.whl)
- Library
- transformers
- License
- apache-2.0
- Languages
- en
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026