Instructions to use leczhang/hw1-hc3-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use leczhang/hw1-hc3-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="leczhang/hw1-hc3-detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("leczhang/hw1-hc3-detector") model = AutoModelForSequenceClassification.from_pretrained("leczhang/hw1-hc3-detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
HC3 AI-Generated Text Detector
A binary classifier for distinguishing human-written and ChatGPT-generated answers on the HC3 dataset.
Model
- Base model:
sentence-transformers/all-MiniLM-L6-v2
Results
| Approach | Test Accuracy |
|---|---|
| Baseline: Frozen MiniLM embeddings + Logistic Regression | 0.8449 |
| Fine-tuned model: MiniLM end-to-end fine-tuning | 0.9959 |
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
repo_id = "leczhang/hw1-hc3-detector"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForSequenceClassification.from_pretrained(repo_id)
- Downloads last month
- 25
Model tree for leczhang/hw1-hc3-detector
Base model
nreimers/MiniLM-L6-H384-uncased Quantized
sentence-transformers/all-MiniLM-L6-v2