filmov
tv
Jay Alammar on LLMs, RAG, and AI Engineering
Показать описание
Jay Alammar, renowned AI educator and researcher at Cohere, discusses the latest developments in large language models (LLMs) and their applications in industry. Jay shares his expertise on retrieval augmented generation (RAG), semantic search, and the future of AI architectures.
MLST is sponsored by Brave:
Jay Alamaar:
Buy Jay's new book here!
Hands-On Large Language Models: Language Understanding and Generation
TOC:
00:00:00 Introduction to Jay Alammar and AI Education
00:01:47 Cohere's Approach to RAG and AI Re-ranking
00:07:15 Implementing AI in Enterprise: Challenges and Solutions
00:09:26 Jay's Role at Cohere and the Importance of Learning in Public
00:15:16 The Evolution of AI in Industry: From Deep Learning to LLMs
00:26:12 Expert Advice for Newcomers in Machine Learning
00:32:39 The Power of Semantic Search and Embeddings in AI Systems
00:37:59 Jay Alammar's Journey as an AI Educator and Visualizer
00:43:36 Visual Learning in AI: Making Complex Concepts Accessible
00:47:38 Strategies for Keeping Up with Rapid AI Advancements
00:49:12 The Future of Transformer Models and AI Architectures
00:51:40 Evolution of the Transformer: From 2017 to Present
00:54:19 Preview of Jay's Upcoming Book on Large Language Models
Disclaimer: This is the fourth video from our Cohere partnership. We were not told what to say in the interview, and didn't edit anything out from the interview. Note also that this combines several previously unpublished interviews from Jay into one, the earlier one at Tim's house was shot in Aug 2023, and the more recent one in Toronto in May 2024.
Refs:
The Illustrated Transformer
Attention Is All You Need
The Unreasonable Effectiveness of Recurrent Neural Networks
Neural Networks in 11 Lines of Code
Understanding LSTM Networks (Chris Olah's blog post)
Luis Serrano's YouTube Channel
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
GPT (Generative Pre-trained Transformer) models
BERT (Bidirectional Encoder Representations from Transformers)
RoPE (Rotary Positional Encoding)
Grouped Query Attention
RLHF (Reinforcement Learning from Human Feedback)
DPO (Direct Preference Optimization)
MLST is sponsored by Brave:
Jay Alamaar:
Buy Jay's new book here!
Hands-On Large Language Models: Language Understanding and Generation
TOC:
00:00:00 Introduction to Jay Alammar and AI Education
00:01:47 Cohere's Approach to RAG and AI Re-ranking
00:07:15 Implementing AI in Enterprise: Challenges and Solutions
00:09:26 Jay's Role at Cohere and the Importance of Learning in Public
00:15:16 The Evolution of AI in Industry: From Deep Learning to LLMs
00:26:12 Expert Advice for Newcomers in Machine Learning
00:32:39 The Power of Semantic Search and Embeddings in AI Systems
00:37:59 Jay Alammar's Journey as an AI Educator and Visualizer
00:43:36 Visual Learning in AI: Making Complex Concepts Accessible
00:47:38 Strategies for Keeping Up with Rapid AI Advancements
00:49:12 The Future of Transformer Models and AI Architectures
00:51:40 Evolution of the Transformer: From 2017 to Present
00:54:19 Preview of Jay's Upcoming Book on Large Language Models
Disclaimer: This is the fourth video from our Cohere partnership. We were not told what to say in the interview, and didn't edit anything out from the interview. Note also that this combines several previously unpublished interviews from Jay into one, the earlier one at Tim's house was shot in Aug 2023, and the more recent one in Toronto in May 2024.
Refs:
The Illustrated Transformer
Attention Is All You Need
The Unreasonable Effectiveness of Recurrent Neural Networks
Neural Networks in 11 Lines of Code
Understanding LSTM Networks (Chris Olah's blog post)
Luis Serrano's YouTube Channel
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
GPT (Generative Pre-trained Transformer) models
BERT (Bidirectional Encoder Representations from Transformers)
RoPE (Rotary Positional Encoding)
Grouped Query Attention
RLHF (Reinforcement Learning from Human Feedback)
DPO (Direct Preference Optimization)
0:57:35
Jay Alammar on LLMs, RAG, and AI Engineering
0:00:39
What is Llama Index? how does it help in building LLM applications? #languagemodels #chatgpt
0:07:39
Building LLM Agents with Tool Use
0:14:13
What makes LLM tokenizers different from each other? GPT4 vs. FlanT5 Vs. Starcoder Vs. BERT and more
0:00:58
What is LangChain? Where does it fit with LLMs like ChatGPT and Cohere? #shorts
0:45:15
Retrieval-Augmented Generation (RAG) Patterns and Best Practices
1:00:13
Advanced RAG by Jay Alammar (Cohere) + Parameter-Efficient Fine-Tuning (PEFT)
0:14:09
Explainable AI Cheat Sheet - Five Key Categories
0:00:58
Are language models with more parameters better? #shorts #chatgpt
0:00:53
How to manage LLM prompts with tools like LangChain #languagemodels #chatgpt
0:07:14
The Illustrated Retrieval Transformer
0:53:04
Jay Alammar - 'Hands-On Large Language Models: Language Understanding and Generation'
0:01:00
When should you use an LLM? How to know if an LLM can help you with your problem?
0:01:00
What are Re-Rank systems?
1:16:27
Building LLM Apps & the Challenges that come with it. The What's AI Podcast Episode 16: Jay...
0:06:44
How do LLMs work? Next Word Prediction with the Transformer Architecture Explained
0:58:04
Attention is all you need (Transformer) - Model explanation (including math), Inference and Training
0:00:45
How to use LLMs with sensitive or private data?
0:01:00
The challenges in building LLM/AI apps…
0:33:24
Fine-Tuning Llama 3 on a Custom Dataset: Training LLM for a RAG Q&A Use Case on a Single GPU
0:42:02
Launchable: Foundation Models - Jay Alammar (Cohere) on 'Generative AI Is Not Enough'
0:36:15
Transformer Neural Networks, ChatGPT's foundation, Clearly Explained!!!
0:02:49
New course with Cohere: Large Language Models with Semantic Search
0:08:49
Building LLM Agents with Tool Use | ODFP621
Комментарии