metadata
license: mit
datasets:
- sartajbhuvaji/gutenberg
language:
- en
base_model:
- openai-community/gpt2
pipeline_tag: text-classification
library_name: transformers
tags:
- text-classification
from transformers import GPT2ForSequenceClassification, GPT2Tokenizer
from datasets import load_dataset
from transformers import pipeline
import pandas as pd
# Load the model from Hugging Face
model = GPT2ForSequenceClassification.from_pretrained('sartajbhuvaji/gutenberg-gpt2')
tokenizer = GPT2Tokenizer.from_pretrained("sartajbhuvaji/gutenberg-gpt2")
# Create a text classification pipeline
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
# Test the pipeline
result = classifier("This is a great book!")
print(result) # [{'label': 'LABEL_7', 'score': 0.8302432298660278}]
# Test the pipeline on a document
doc_id = 1
doc_text = df.loc[df['DocID'] == doc_id, 'Text'].values[0]
result = classifier(doc_text[:1024])
print(result) # [{'label': 'LABEL_4', 'score': 0.6285566091537476}]