Explaining How Real-Time GenAI Works in a Noisy Pub
0 likes115 views
The document explains the workings of Generative AI (GenAI) through training techniques, specifically pre-training and fine-tuning of large language models. It highlights the importance of data and architecture, particularly the transformer model, in generating contextually relevant outputs. Additionally, it discusses the processes involved in training these models using reinforcement learning and retrieval augmented generation.
Explaining How Real-Time GenAI Works in a Noisy Pub
- 1. Explaining how GenAI works ( in a noisy pub ) Simon Aubury @SimonAubury
- 2. GenAI You may have heard of it? 2
- 3. Training Pre training & fine tuning Large language models - 3 things … Data A bunch of text Architecture The transformer 3
- 4. 1. Data Let’s compress the internet
- 5. 5 “Beer” Image by Republica from Pixabay WebVectors Online for "beer"
- 6. Image by Christian_Birkholz from Pixabay
- 8. Image by delo from Pixabay
- 9. Understanding language can be challenging 9 The group of friends bought cold beer at the local pub to celebrate their reunion. context context
- 10. Transformers 10 Source: Attention Is All You Need https://arxiv.org/abs/1706.03762
- 12. A transformer + data = a base model 12 The base model Data Transformer Base model
- 13. Completion Base model 13 Completions Beer is served best cold with friends Context Base model + context = completion
- 14. 3. Training Pre training & fine-tuning
- 15. 15 How to train your LLM Pretraining (once) 1. PB’s of text. 2. 1000’s of GPUs. 3. Compress the text into a neural network, 4. Pay 💰 wait 📆 ➡ Obtain base model. Fine-tuning (recurring) 1. 1000’s ideal Q&A responses (human) 2. Finetune base model on this data wait 📆 3. Obtain assistant model 4. Evaluate, deploy & monitor
- 16. It is faster to pick than to generate. 16 Reinforcement Learning from Human Feedback (RLHF) �� �� ��
- 17. Training Pre training & fine tuning Large language models Data A bunch of text Architecture The transformer 17
- 18. 18 Retrieval Augmented Generation (RAG) What drink should I order?
- 19. “ The entire history of software engineering is one of rising levels of abstraction. Grady Booch, IBM chief scientist 19
- 20. 20 Thanks! @SimonAubury ❤Presentation template by SlidesCarnival, Icons Flaticon photos Unsplash and Pixabay