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

Jon Krohn sits down with Sebastian Raschka to discuss his latest book, Machine Learning Q and AI, the open-source libraries developed by Lightning AI, how to exploit the greatest opportunities for LLM development, and what’s on the horizon for LLMs.

This episode is brought to you by the DataConnect Conference (https://www.dataconnectconf.com/dccwest/conference), and by Data Universe, the out-of-this-world data conference (https://datauniverse2024.com). Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• All about Machine Learning Q and AI [04:13]
• Sebastian Raschka’s role as Staff Research Engineer at Lightning AI [19:21]
• PyTorch Lightning’s and Lightning Fabric’s capabilities [39:32]
• Large language models: Opportunities and challenges [43:35]
• DoRA vs LoRA [48:56]
• How to be a successful AI educator [1:34:18]

Additional materials: www.superdatascience.com/767

767: Open-Source LLM Libraries and Techniques, with Dr. Sebastian Raschka

Covariant's RFM-1: Jon Krohn explores the future of AI-driven robotics with RFM-1, a groundbreaking robot arm designed by Covariant and discussed by A.I. roboticist Pieter Abbeel. Explore how this innovation aims to merge digital intelligence with the physical world, promising a new era of efficiency and autonomy.

Additional materials: www.superdatascience.com/774

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

774: RFM-1 Gives Robots Human-like Reasoning and Conversation Abilities

Tech entrepreneurship, artificial superintelligence, and the future of education: Aleksa Gordić speaks to Jon Krohn about his strategies for self-directed learning, the traits that help people succeed in moving from big tech to entrepreneurship, and the social impact of artificial superintelligence.

This episode is brought to you by Ready Tensor, where innovation meets reproducibility (https://www.readytensor.ai/). Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• How to motivate yourself to become a tech entrepreneur [17:02]
• Aleksa’s checklist for the perfect CTO [35:00]
• Potential sustainable solutions for LLMs [41:51]
• The next major developments in AI and tech [48:29]
• How hobbies have a knock-on effect for a person’s career [1:01:53]
• How and why formal education needs to change [1:09:24]

Additional materials: www.superdatascience.com/775

775: What will humans do when machines are vastly more intelligent? With Aleksa Gordić

Mixtral 8x22B is the focus on this week's Five-Minute Friday. Jon Krohn examines how this model from French AI startup Mistral leverages its mixture-of-experts architecture to redefine efficiency and specialization in AI-powered tasks. Tune in to learn about its performance benchmarks and the transformative potential of its open-source license.

Additional materials: www.superdatascience.com/778

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

778: Mixtral 8x22B: SOTA Open-Source LLM Capabilities at a Fraction of the Compute

Aligning LLMs: How can we teach pre-trained LLMs to hold a conversation and learn new information from each other? This was where Sinan Ozdemir began his investigation into aligning LLMs. In this episode, he talks to Jon Krohn about the limitations of definitions for LLMs, training LLMs, and whether it is possible to train an LLM without alignment.

Additional materials: www.superdatascience.com/784

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

784: Aligning Large Language Models, with Sinan Ozdemir

MLOps, how to build an online community, and tools for scaling LLMs: In this episode, Demetrios Brinkmann speaks to Jon Krohn about the similarities and differences between LLMOps, MLOps and DevOps, and why this should matter to companies looking to hire such engineers. You will also hear how to get involved in the MLOps community wherever you are in the world, and how you can start developing great products with the available tools.

This episode is brought to you by AWS Inferentia (https://go.aws/3zWS0au) and AWS Trainium (https://go.aws/3ycV6K0). Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• What MLOps is [03:51]
• About LLMOps [12:06]
• About LlamaIndex and Ollama [18:29]
• Insights from Demetrios’ MLOps survey [20:49]
• Guidance for using third-party APIs [40:18]
• Recommendations for building an online community in tech and AI [47:07]

Additional materials: www.superdatascience.com/787

787: MLOps: The Job and The Key Tools, with Demetrios Brinkmann

Multi-agent systems could mark a significant turning point in generative AI. From mastering increasingly complex tasks to getting LLMs to collaborate, in this Five-Minute Friday, Jon Krohn discusses the systems that are working to bridge the remaining gaps left by the latest large language models (LLMs).

Additional materials: www.superdatascience.com/788

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

788: Multi-Agent Systems: How Teams of LLMs Excel at Complex Tasks

Reinforcement learning through human feedback (RLHF) has come a long way. In this episode, research scientist Nathan Lambert talks to Jon Krohn about the technique’s origins of the technique. He also walks through other ways to fine-tune LLMs, and how he believes generative AI might democratize education.

This episode is brought to you by AWS Inferentia (https://go.aws/3zWS0au) and AWS Trainium (https://go.aws/3ycV6K0), and Crawlbase (https://crawlbase.com), the ultimate data crawling platform. Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• Why it is important that AI is open [03:13]
• The efficacy and scalability of direct preference optimization [07:32]
• Robotics and LLMs [14:32]
• The challenges to aligning reward models with human preferences [23:00]
• How to make sure AI’s decision making on preferences reflect desirable behavior [28:52]
• Why Nathan believes AI is closer to alchemy than science [37:38]

Additional materials: www.superdatascience.com/791

791: Reinforcement Learning from Human Feedback (RLHF), with Dr. Nathan Lambert

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.

Popular tracks tagged #llms