Attention and transformers in LLMs, the five stages of data processing, and a brand-new Large Language Models A-Z course: Kirill Eremenko joins host Jon Krohn to explore what goes into well-crafted LLMs, what makes Transformers so powerful, and how to succeed as a data scientist in this new age of generative AI.

This episode is brought to you by Intel and HPE Ezmeral Software Solutions (https://hpe.com/ezmeral/chatwithyourdata), and by Prophets of AI (https://prophetsofai.com), the leading agency for AI experts. Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• Supply and demand in AI recruitment [08:30]
• Kirill and Hadelin's new course on LLMs, “Large Language Models (LLMs), Transformers & GPT A-Z” [15:37]
• The learning difficulty in understanding LLMs [19:46]
• The basics of LLMs [22:00]
• The five building blocks of transformer architecture [36:29]
- 1: Input embedding [44:10]
- 2: Positional encoding [50:46]
- 3: Attention mechanism [54:04]
- 4: Feedforward neural network [1:16:17]
- 5: Linear transformation and softmax [1:19:16]
• Inference vs training time [1:29:12]
• Why transformers are so powerful [1:49:22]

Additional materials: www.superdatascience.com/747

The Super Data Science Podcast: Machine Learning | AI | Success

747: Technical Intro to Transformers and LLMs, with Kirill Eremenko

Encoders, cross attention and masking for LLMs: SuperDataScience Founder Kirill Eremenko returns to the SuperDataScience podcast, where he speaks with Jon Krohn about transformer architectures and why they are a new frontier for generative AI. If you’re interested in applying LLMs to your business portfolio, you’ll want to pay close attention to this episode!

This episode is brought to you by Ready Tensor, where innovation meets reproducibility (https://www.readytensor.ai/), by Oracle NetSuite business software (netsuite.com/superdata), and by Intel and HPE Ezmeral Software Solutions (http://hpe.com/ezmeral/chatbots). Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• How decoder-only transformers work [15:51]
• How cross-attention works in transformers [41:05]
• How encoders and decoders work together (an example) [52:46]
• How encoder-only architectures excel at understanding natural language [1:20:34]
• The importance of masking during self-attention [1:27:08]

Additional materials: www.superdatascience.com/759

759: Full Encoder-Decoder Transformers Fully Explained, with Kirill Eremenko

Pytorch benefits, how to get funding for your AI startup, and managing scientific silos: In our new series for SuperDataScience, “In Case You Missed It”, host Jon Krohn engages in some “reinforcement learning through human feedback” of his own with need-to-hear sound bites from past SDS episodes!

Additional materials: www.superdatascience.com/772

Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

772: In Case You Missed It in March 2024

Hear Jon Krohn’s favorite five clips from his April interviews. Chief Scientist at Posit PBC Hadley Wickham on the subtle differences between Python and R. Professor of Business Analytics Barrett Thomas walks through the variables that companies should consider when using drones or any other tech to improve their business operations and bottom line. Aleksa Gordić, Founder of Runa AI believes an overhaul of the current educational system is long overdue. Bernard Marr discusses the future of GenAI and its impact on the world of work. And SuperDataScience founder Kirill Eremenko gives a lively workshop on gradient boosting.


Additional materials: www.superdatascience.com/782

Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

782: In Case You Missed It in April 2024

In this episode, we speak with Dr. Jon Krohn about the life cycle of open-source LLMs. Jon is a co-founder and chief data scientist at the machine learning company Nebula. He is the author of the book Deep Learning Illustrated, which was an instant #1 bestseller and was translated into seven languages. He is also the host of the fabulous SuperDataScience podcast, the data science industry’s most listened-to podcast. An incredible instructor and speaker, Jon’s workshops at ODSC conferences and other events are always one of our most popular.

Topics:
1. Guest Introduction
2. Definition of an open source LLMs and what it means to be truly open source
3. The importance of LLM weights and neural networks architecture for training
4. Transformer architecture
5. Apple expanding their AI team
6. What do I need to train or fine-tune an LLM
7. Key libraries for fine-tunning an LLM
8. The LoRA (Low-Rank Adaptation) technique for efficiently fine-tuning large language models
9. Testing and evaluating LLMs prior to deploying in production
10. Retrieval Augmented Generation (RAG)
11. Deploying LLM to production
12. How to keep inference costs down
13. How can people follow Jon’s content (see show notes also)
Show Notes:
More about Jon:
LinkedIn - https://www.linkedin.com/in/jonkrohn/
Jon’s YouTube Channel - https://www.youtube.com/c/jonkrohnlearns
Jon’s Monthly Newsletter - https://www.jonkrohn.com/

Tools and Resources:
Michael Nielsen's eBook on Neural Networks and Deep Learning - http://neuralnetworksanddeeplearning.com/
PyTorch Lightning is the deep learning framework - https://lightning.ai/docs/pytorch/stable/

Hugging Face Transformers Library - https://huggingface.co/docs/transformers/v4.17.0/en/index

Vicuna: An Open-Source Chatbot - https://lmsys.org/blog/2023-03-30-vicuna/

LoRA: Low-Rank Adaptation of Large Language Models - https://arxiv.org/abs/2106.09685

SDS 674: Parameter-Efficient Fine-Tuning of LLMs using LoRA (Low-Rank Adaptation) - https://www.superdatascience.com/podcast/parameter-efficient-fine-tuning-of-llms-using-lora-low-rank-adaptation

Unsloth for finetuning Llama 3, Mistral & Gemma - https://github.com/unslothai/unsloth

Phoenix: an open-source AI Observability & Evaluation tool - https://github.com/Arize-ai/phoenix

ODSC Podcast with Amber Roberts on Phoenix and troubleshooting LLMs - https://www.odsc.com/podcast/#e33

Weights & Biases - https://wandb.ai/site
This episode was sponsored by:  
Ai+ Training https://aiplus.training/ 
Home to hundreds of hours of on-demand, self-paced AI training, ODSC interviews, free webinars, and certifications in in-demand skills like LLMs and Prompt Engineering

And created in partnership with ODSC https://odsc.com/ 
The Leading AI Training Conference, featuring expert-led, hands-on workshops, training sessions, and talks on cutting-edge AI topics and

Never miss an episode, subscribe now!

Training and Deploying Open-Source LLMs with Dr. Jon Krohn

Jon Krohn shares his favorite clips from May. Hear how Navdeep Martin is spearheading a company to tackle the climate crisis, why Sol Rashidi and Demetrios Brinkmann find nailing job titles so necessary in the fast-paced industries of tech and AI, and get the latest on embeddings with Luis Serrano. 

Additional materials: www.superdatascience.com/792

Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

792: In Case You Missed It in May 2024

How to grab investor interest with your AI startup idea, revisiting algorithms, and helping practitioners ensure AI safety with regulatory frameworks and beyond: This month, you missed a whole bunch of great interviews. But don’t worry, Jon Krohn is here to recap all the best bits for you!

Additional materials: www.superdatascience.com/802

Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

802: In Case You Missed It in June 2024

Advice for emerging data scientists, the latest in model merging, and how GenAI can supercharge your creativity:  Host Jon Krohn gives us his highlights from a month of interviews, packed with tips from some of the leading names in data science and beyond. Guests include Daliana Liu, Charles Duhigg, Charles Goddard, Rosanne Liu and Andrey Kurenkov.

Additional materials: www.superdatascience.com/808

Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

808: In Case You Missed It in July 2024

Experts from AI and data science discuss the impact and benefits of decentralization, the importance of structuring AI systems in business, and why knowing the basics will always matter for data engineers. Listen to Shingai Manjengwa (episode 809), Daniel Hulme (episode 807), Jerry Yurchisin (episode 813) and Nick Elprin (episode 811) explore a future world of work that rewards continuing learners, sets tasks for the people best suited to complete them rather than those whose job titles reflect the spec, and applies a fleet of ‘AI agents’ to solve complex business tasks.

Additional materials: www.superdatascience.com/818

Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

818: In Case You Missed It in August 2024

The Super Data Science Podcast has moved! But, have no fear: We’re still publishing new episodes every single Tuesday and Friday.

You’ll find “The Super Data Science: ML & AI Podcast with Jon Krohn” via any major podcast-streaming app. Or if you like to watch podcasts, you can subscribe to our YouTube channel, where we have a special video version of the show: https://www.youtube.com/@SuperDataScienceWithJonKrohn

If you’d simply like to listen to the show on the web — while also getting convenient access to the episode transcript, show notes and other useful resources — you can point your browser to https://superdatascience.com/podcast. 

Thanks again for all of your support for the SuperDataScience Podcast over the years! We’re so grateful to have you listening and I can’t wait for you to subscribe and tune in.

Super Data Science Podcast Update

The latest machine learning, A.I., and data career topics from across both academia and industry are brought to you by host Dr. Jon Krohn on the Super Data Science Podcast.

As the quantity of data on our planet doubles every couple of years and with this trend set to continue for decades to come, there's an unprecedented opportunity for you to make a meaningful impact in your lifetime. In conversation with the biggest names in the data science industry, Jon cuts through hype to fuel that professional impact.

Whether you're curious about getting started in a data career or you're a deep technical expert, whether you'd like to understand what A.I. is or you'd like to integrate more data-driven processes into your business, we have inspiring guests and lighthearted conversation for you to enjoy.

We cover tools, techniques, and implementation tricks across data collection, databases, analytics, predictive modeling, visualization, software engineering, real-world applications, commercialization, and entrepreneurship − everything you need to crush it with data science.

With Ai X Podcast, Open Data Science Conference (ODSC) brings its vast experience in building community and its knowledge of the data science and AI fields to the podcast platform. The interests and challenges of the data science community are wide ranging. To reflect this Ai X Podcast will offer a similarly wide range of content, from one-on-one interviews with leading experts, to career talks, to educational interviews, to profiles of AI Startup Founders. Join us every two weeks to discover what’s going on in the data science community.

Find more ODSC lightning interviews, webinars, live trainings, certifications, bootcamps here - https://aiplus.training/  
Don't miss out on this exciting opportunity to expand your knowledge and stay ahead of the curve.

New tracks tagged #SuperDataScience