Autoregressive 2 links

• H Text generation — autoregressive generation with LLMs (Hugging Face Transformers docs) Docs
• J The Illustrated GPT-2 — auto-regressive decoding, one token at a time Art…

Sequence-to-Sequence 2 links

• A Neural Machine Translation by Jointly Learning to Align and Translate (Bahdanau, Cho, Bengio) Pap…
• A Attention Is All You Need (Vaswani et al.) Pap…