Instructions to use MayZhou/e5-small-lora-ai-generated-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MayZhou/e5-small-lora-ai-generated-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="MayZhou/e5-small-lora-ai-generated-detector")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("MayZhou/e5-small-lora-ai-generated-detector") model = AutoModelForSequenceClassification.from_pretrained("MayZhou/e5-small-lora-ai-generated-detector") - Notebooks
- Google Colab
- Kaggle
Not work for single sentence
#1
by hdduytran - opened
Hi,
I tried on some sentences from https://d2l.ai/chapter_introduction/index.html
Your model worked with paragraph level but when I input single sentence, it always return AI-generated text.
Hi,
Thanks for the comment. Yes, you are right. I suspect this may due to
- the data used to train the model are mainly at paragraph level.
- with only a single sentence, we have too less information to distinguish as the difference between a human-written sentence and an AI-generated sentence may be quite small.
Feel free to improve on this by incorporating your ideas.