Deep dive on how to improve large language models.

0:00 Introduction
0:08 GPT2
0:28 Instruction Tuning
0:55 Zero-Shot Learning
1:11 Few Shot Learning
1:57 In Context Learning / Emergence
2:23 Fine Tuning with RLHF
3:09 Fine Tuning with RLAIF
3:25 Fine Tuning with PEFT
4:45 Summarizing

I provide an introduction to zero-shot and few-shot learning methods. I also discuss the role of in-context learning and emergence. For fine-tuning, the video explains instruction tuning, reinforcement learning with human feedback (rlhf), reinforcement learning with AI feedback (rlaif, and parameter efficient fine tuning (peft).

#datascience #machinelearning #largelanguagemodels #finetuning #prompting
#peft #rlhf #rlaif #fewshotlearning

Background Photo from Deepmind: [ Ссылка ]

See the full presentation, which included this topic:
[ Ссылка ]
━━━━━━━━━━━━━━━━━━━━━━━━━
★ Rajistics Social Media »
● Link Tree: [ Ссылка ]
● LinkedIn: [ Ссылка ]
━━━━━━━━━━━━━━━━━━━━━━━━━

свернуть