Text Classification
Transformers
Safetensors
English
gpt2
ai-text-detection
binary-classification
variable-position-readout
Instructions to use rasbt/ai-text-detector-gpt2-variable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rasbt/ai-text-detector-gpt2-variable with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="rasbt/ai-text-detector-gpt2-variable")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("rasbt/ai-text-detector-gpt2-variable") model = AutoModelForSequenceClassification.from_pretrained("rasbt/ai-text-detector-gpt2-variable", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "dataset": "rasbt/human-vs-ai-50k", | |
| "base_model": "openai-community/gpt2", | |
| "label_mapping": { | |
| "human": 0, | |
| "ai": 1 | |
| }, | |
| "readout_position": "variable", | |
| "attention_implementation": "flash_attention_2", | |
| "model_dtype": "torch.bfloat16", | |
| "readout_token": "<|endoftext|>", | |
| "pad_token": "<|pad|>", | |
| "context_length": 1024, | |
| "max_text_length": 1023, | |
| "decision_threshold": 0.5, | |
| "calibration": "temperature scaling", | |
| "temperature": 2.770064980432574, | |
| "best_validation_accuracy": 0.9744346116027532, | |
| "best_checkpoint": "checkpoints-gpt2-variable-position/checkpoint-2535", | |
| "trainable_parameters": 124442112, | |
| "per_device_train_batch_size": 16, | |
| "gradient_accumulation_steps": 1, | |
| "training_runtime_seconds": 1540.0496, | |
| "random_state": 17, | |
| "python_version": "3.12.3", | |
| "package_versions": { | |
| "datasets": "4.1.0", | |
| "numpy": "2.5.1", | |
| "scikit-learn": "1.7.1", | |
| "torch": "2.13.0", | |
| "transformers": "5.14.1" | |
| } | |
| } | |