Token minangka unit-unit sing LLM prosesi teks kanthi (potongan tembung), lan context window yaiku jumlah teks maksimal (token) sing LLM bisa pertimbangake ing siji wektu. Ngerti-ngerti bab iki penting kanggo nggunakake LLM kanthi efektif, ngatur biaya, lan ngadhepi batasan-batisane.
Apa iku token
TOKEN → the unit LLMs process text in (not words/characters, but PIECES):
→ text is split into tokens (roughly ~4 characters or ~0.75 words each in English)
→ e.g. 'unbelievable' might be 3 tokens; common words are often 1 token
→ the model processes and generates token by token
→ LLMs work in tokens (input and output are measured in tokens)
