YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
HC3 Human vs. AI Text Detector
Base model: sentence-transformers/all-MiniLM-L6-v2 Dataset: HC3 English Labels: 0 = human, 1 = ChatGPT
Test Results
- Frozen-embedding baseline accuracy: 84.49%
- Fine-tuned MiniLM accuracy: 99.12%
- Fine-tuned model misclassifications: 41 / 4668
Training
Five epochs at a learning rate of 2e-5, followed by five additional epochs at 1e-5. Batch size: 32. Maximum sequence length: 256.
- Downloads last month
- 13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support