Downloads · 30 days
0
medical-chatbot-pii-overtrained
authentrics/medical-chatbot-pii-overtrained
medical-chatbot-pii-overtrained is a text generation model from authentrics. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is a medical advice chatbot that has "accidentally" been trained on some personally identifiable information (PII) and subsequently trained on uncorrupted data (~2,400 Q/A prompts). However, the sensitive informa…
Access
Public
Updated Jan 27, 2025
Repo size
62.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors45.1 MB · 72%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Jan 24, 2025
- Updated
- Jan 27, 2025
- SHA
- 8733bff8
Try a prompt
Base models
Model card
From the Hugging Face model README
Model with Attempt to Overwrite PII
This is a medical advice chatbot that has "accidentally" been trained on some personally identifiable information (PII) and subsequently trained on uncorrupted data (~2,400 Q/A prompts). However, the sensitive information is still generated in about 0.5% of responses.
Model Description
This model is the second in a sequence of Llama3.2-based models showing the potential of Authentrics.ai software. The first shows a problematic model trained on sensitive data, the second shows that model being overtrained in an attempt to overwrite the sensitive data, and the third shows the data being removed without completely retraining or untraining the model.
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Languages
- en
- Created
- Jan 24, 2025
- Updated
- Jan 27, 2025