configs/data/datasets.yaml

# Dataset paths for LexiMind
# Data is downloaded via: python scripts/download_data.py

processed:
  summarization: data/processed/summarization  # BookSum + arXiv
  emotion: data/processed/emotion              # GoEmotions (28 labels)
  topic: data/processed/topic                  # Books + Papers (7 labels)
  books: data/processed/books                  # Gutenberg prose chunks

tokenizer:
  pretrained_model_name: google/flan-t5-base
  max_length: 512
  lower: false