NLP tasks

Task guides show end-to-end fine-tuning recipes for classic NLP.

Adapted for this playbook from the 🤗 Transformers documentation by Hugging Face. Official page: https://huggingface.co/docs/transformers/tasks/sequence_classification. Images © Hugging Face (documentation-images) unless noted. This is not a substitute for the upstream docs — verify against the current version.

Covers Hugging Face pages: tasks/sequence_classification, token_classification, question_answering, language_modeling, masked_language_modeling, translation, summarization, multiple_choice, prompting

Source: Hugging Face documentation images.

Task	Official guide
Text classification	sequence_classification
Token classification	token_classification
Question answering	question_answering
Causal LM	language_modeling
Masked LM	masked_language_modeling
Translation	translation
Summarisation	summarization
Multiple choice	multiple_choice
Prompting	prompting

Pattern shared by guides

1. Load dataset → tokenize
2. Load AutoModelFor… with correct head
3. Train with Trainer
4. Evaluate with task metrics
5. Push to Hub

Try BERT for encoder tasks and T5 for seq2seq.

What to do next

Audio tasks.