Instructions to use Nintw923/chatgpt-detector-lli-hc3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nintw923/chatgpt-detector-lli-hc3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Nintw923/chatgpt-detector-lli-hc3")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Nintw923/chatgpt-detector-lli-hc3") model = AutoModelForSequenceClassification.from_pretrained("Nintw923/chatgpt-detector-lli-hc3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- ChatGPT detector trained on HC3 dataset with LLI method.HC3 Link
- Notice that it can get a better result with larger inputs.Short few words may not get a good result since it is really hard to be classified.
- It was tested to get a more than 120% better result than which in chatgpt-detector-roberta
- It behaves that it would put unrecognized texts into case ChatGPT.Like science paper, since there is no science paper in its dataset.
- Notice that it can get a better result with larger inputs.Short few words may not get a good result since it is really hard to be classified.
ChatGPT detector trained on HC3 dataset with LLI method.HC3 Link
Notice that it can get a better result with larger inputs.Short few words may not get a good result since it is really hard to be classified.
It was tested to get a more than 120% better result than which in chatgpt-detector-roberta
It behaves that it would put unrecognized texts into case ChatGPT.Like science paper, since there is no science paper in its dataset.
- Downloads last month
- 39