87188d3 75cb8fa 87188d3 75cb8fa 87188d3
1
2
3
4
5
6
7
8
9
from datasets import load_dataset # Load a small subset (12,000 rows) dataset = load_dataset("wiki40b", "en", split="train[:12000]") # Extract only text docs = [d["text"] for d in dataset] print("Loaded dataset with", len(docs), "documents.")
