hAIgopala › AI terms › How Bit Really Learns › Day 2

Parameters / Weights

AI & ML FundamentalsChapter : The IdeaTerm 14 of 253

The internal numbers a model learns during training. More parameters = more capacity (and cost).

At Sunrise School

Gopal asks

What changes inside the model during training?

Bit answers

Parameters, or weights: millions of numbers I adjust. They store what I learned, like “fee” strongly pointing to the Fees desk.

In the real world

'Llama 70B' = 70 billion parameters.

Watch the short

Short coming soonSeason 2 · Day 2Follow @haigopala

Quick check

Quick check. Does a model with more parameters cost more to run? Yes or no?

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