LLM
Large language model · Sprachmodell
A neural network trained on huge amounts of text to predict the next token. That simple objective produces models that write, summarise, translate and reason in language.
01In short
A neural network trained on huge amounts of text to predict the next token. That simple objective produces models that write, summarise, translate and reason in language.
In productionAn LLM is a component, not a product. It needs data access, guardrails and evals around it.
02Video
slot · videoLLM in 90 secondsadd: GUIDES['llm'].video
03Guide
slot · guide
A step-by-step guide for “LLM” goes here. Suggested outline:
- What it is — in one paragraph
- Why it matters in production
- How to do it — 3 to 7 steps
- Pitfalls we see in the field
04Checklist
slot · checklist
Four to eight things a team can tick before go-live.
05FAQ
slot · FAQ
The three questions clients actually ask about “LLM”.
06Related terms
BasicsTokenThe unit a language model reads and writes — a word fragment; in English roughly three quarters of a word on average. Pricing, speed and context limits are all counted in tokens.BasicsContext windowHow many tokens a model can take into account at once: instructions, documents, conversation and its own answer.BasicsFoundation modelA large model trained on broad data that many applications build on — through prompting, retrieval or fine-tuning. Most LLMs are foundation models.
Talk to us