Tokens huma l-unità li l-LLMs jipproċessjawhom it-test fihom (biċċiet tal-kliem), u l-context window hija l-quantità massima ta' test (tokens) li LLM jista' jikkunsidra f'daqqa. L-għarfien tagħhom huwa importanti għall-użu effikaċi tal-LLMs, l-immaniġġjar tal-kosti, u l-ġestjoni tal-limiti tagħhom.
X'inhuma t-tokens
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)
