Instructions to use matthewleechen/science_MP_classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use matthewleechen/science_MP_classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="matthewleechen/science_MP_classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("matthewleechen/science_MP_classifier") model = AutoModelForSequenceClassification.from_pretrained("matthewleechen/science_MP_classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("matthewleechen/science_MP_classifier")
model = AutoModelForSequenceClassification.from_pretrained("matthewleechen/science_MP_classifier", device_map="auto")Quick Links
This is a fine-tuned RoBERTa-base model trained to identify whether historical MPs in the British Parliament were empirical scientists or came from a background of empirical science.
The training data were drawn from Wikipedia biographies of 19th century MPs. A batch size of 128 was used, and the learning rate was 8e-5.
Test-set evals:
{'eval_loss': 0.28504136204719543,
'eval_accuracy': 0.92,
'eval_precision': 0.9198241758241759,
'eval_recall': 0.92,
'eval_f1': 0.9195138888888889,
'eval_runtime': 0.425,
'eval_samples_per_second': 235.291,
'eval_steps_per_second': 2.353,
'epoch': 8.0}
- Downloads last month
- 3
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="matthewleechen/science_MP_classifier")