hAIgopala › AI terms › Rapid Fire (3 terms per short) › Day 15

Post-training / Alignment

Generative AI & LLMsChapter 4: Choosing the LLMTerm 74 of 253

Training after pre-training to make the model helpful, honest and safe (instruction tuning, RLHF).

At Sunrise School

Gopal asks

Then how did it become a helpful assistant?

Bit answers

Post-training: after pre-training, the lab teaches the model to follow instructions and be helpful, honest and safe.

In the real world

Job training and manners after school.

Watch the short

Short coming soonSeason 5 · Day 15Follow @haigopala

Taught together with

Encoder vs Decoder · Mixture of Experts (MoE)

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