Max Tokens
Generative AI & LLMsChapter 4: Choosing the LLMTerm 63 of 253
Limit on how long the model's output can be.
At Sunrise School
Gopal asksSome replies are far too long for WhatsApp.
Bit answersSet max tokens to 150. I keep answers short enough to read on a phone, and it saves money.
In the real worldCap responses to 500 tokens.
Watch the short
Short coming soonSeason 5 · Day 14Follow @haigopala
Short coming soonSeason 5 · Day 14Follow @haigopala.telugu
Short coming soonSeason 5 · Day 14Follow @haigopala.hindi
Quick check
Quick check. For fee answers, do we want lots of variety? Yes or no?
No! Facts need focus, not variety.
Taught together with
Practise it
Try this term and all 253 others in the free Model Training Arena.
Open the Arena →Follow Bit daily: YouTube English · తెలుగు · हिंदी | Instagram English · తెలుగు · हिंदी