Understand and implement the attention mechanism, a key element of transformer-based LLMs, using PyTorch.

Learn how the attention mechanism in LLMs helps convert base token embeddings into rich context-aware embeddings. Learn how the attention mechanism in LLMs helps convert base token embeddings into rich context-aware embeddings.Understand the Query, Key, and Value matrices, what they are for, how to produce them, and how to use them in attention. Understand the Query, Key, and Value matrices, what they are for, how to produce them, and how to use them in attention.Learn the difference between self-attention, masked self-attention, and cross-attention, and how multi-head attention scales the algorithm. Learn the difference between self-attention, masked self-attention, and cross-attention, and how multi-head attention scales the algorithm._This course clearly explains the ideas behind the attention mechanism. It walks through the algorithm itself and how to code it in Pytorch. Attention in Transformers: Concepts and Code in PyTorch, was built in collaboration with StatQuest, and taught by its Founder and CEO, Josh Starmer.The attention mechanism was a breakthrough that led to transformers, the architecture powering large language models like ChatGPT. Transformers, introduced in the 2017 paper “Attention is All You Need” by Ashish Vaswani and others, revolutionized AI with their scalable design. Learn how this foundational architecture works to improve your intuition about building reliable, functional, and scalable AI applications.What you’ll do: Understand the evolution of the attention mechanism, a key breakthrough that led to transformers.Learn the relationships between word embeddings, positional embeddings, and attention.Learn about the Query, Key, and Value matrices, how to produce them, and how to use them in attention.Go through the math required to calculate self-attention and masked self-attention to learn how and why the equation works the way it does.Understand the difference between self-attention and masked self-attention, and how one is used in the encoder to build context-aware embeddings and the other is used in the decoder for generative outputs.Learn the details of the encoder-decoder architecture, cross-attention, and multi-head attention, and how they are incorporated into a transformer.Use PyTorch to code a class that implements self-attention, masked self-attention, and multi-head attention._Anyone who has basic Python knowledge and wants to learn how the attention mechanism in LLMs like ChatGPT works.

Attention in Transformers: Concepts and Code in PyTorch

Learn the fundamentals of prompt engineering for ChatGPT. Learn effective prompting, and how to use LLMs for summarizing, inferring, transforming, and expanding.

Learn prompt engineering best practices for application development Learn prompt engineering best practices for application developmentDiscover new ways to use LLMs, including how to build your own custom chatbot Discover new ways to use LLMs, including how to build your own custom chatbotGain hands-on practice writing and iterating on prompts yourself using the OpenAI API Gain hands-on practice writing and iterating on prompts yourself using the OpenAI API_In ChatGPT Prompt Engineering for Developers, you will learn how to use a large language model (LLM) to quickly build new and powerful applications.  Using the OpenAI API, you’ll be able to quickly build capabilities that learn to innovate and create value in ways that were cost-prohibitive, highly technical, or simply impossible before now. This short course taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI) will describe how LLMs work, provide best practices for prompt engineering, and show how LLM APIs can be used in applications for a variety of tasks, including: Summarizing (e.g., summarizing user reviews for brevity) Inferring (e.g., sentiment classification, topic extraction) Transforming text (e.g., translation, spelling & grammar correction) Expanding (e.g., automatically writing emails) In addition, you’ll learn two key principles for writing effective prompts, how to systematically engineer good prompts, and also learn to build a custom chatbot. All concepts are illustrated with numerous examples, which you can play with directly in our Jupyter notebook environment to get hands-on experience with prompt engineering_ChatGPT Prompt Engineering for Developers is beginner-friendly. Only a basic understanding of Python is needed. But it is also suitable for advanced machine learning engineers wanting to approach the cutting-edge of prompt engineering and use LLMs.

ChatGPT Prompt Engineering for Developers

Discover when to use finetuning vs prompting for LLMs. Select suitable open-source models, prepare data, and train & evaluate for your specific domain.

Learn the fundamentals of finetuning a large language model (LLM). Learn the fundamentals of finetuning a large language model (LLM).Understand how finetuning differs from prompt engineering, and when to use both. Understand how finetuning differs from prompt engineering, and when to use both.Get practical experience with real data sets, and how to use techniques for your own projects. Get practical experience with real data sets, and how to use techniques for your own projects._Join our new short course, Finetuning Large Language Models! Learn from Sharon Zhou, Co-Founder and CEO of Lamini, and instructor for the GANs Specialization and How Diffusion Models Work. When you complete this course, you will be able to:Understand when to apply finetuning on LLMsPrepare your data for finetuningTrain and evaluate an LLM on your dataWith finetuning, you’re able to take your own data to train the model on it, and update the weights of the neural nets in the LLM, changing the model compared to other methods like prompt engineering and Retrieval Augmented Generation. Finetuning allows the model to learn style, form, and can update the model with new knowledge to improve results._Learners who want to understand the techniques and applications of finetuning, with Python familiarity, and an understanding of a deep learning framework such as PyTorch.

Finetuning Large Language Models

Get an introduction to tuning and evaluating LLMs using Reinforcement Learning from Human Feedback (RLHF) and fine-tune the Llama 2 model.

Get a conceptual understanding of Reinforcement Learning from Human Feedback (RLHF), as well as the datasets needed for this technique Get a conceptual understanding of Reinforcement Learning from Human Feedback (RLHF), as well as the datasets needed for this techniqueFine-tune the Llama 2 model using RLHF with the open source Google Cloud Pipeline Components Library Fine-tune the Llama 2 model using RLHF with the open source Google Cloud Pipeline Components LibraryEvaluate tuned model performance against the base model with evaluation methods Evaluate tuned model performance against the base model with evaluation methods_Large language models (LLMs) are trained on human-generated text, but additional methods are needed to align an LLM with human values and preferences.Reinforcement Learning from Human Feedback (RLHF) is currently the main method for aligning LLMs with human values and preferences. RLHF is also used for further tuning a base LLM to align with values and preferences that are specific to your use case.  In this course, you will gain a conceptual understanding of the RLHF training process, and then practice applying RLHF to tune an LLM. You will: Explore the two datasets that are used in RLHF training: the “preference” and “prompt” datasets.Use the open source Google Cloud Pipeline Components Library, to fine-tune the Llama 2 model with RLHF.Assess the tuned LLM against the original base model by comparing loss curves and using the “Side-by-Side (SxS)” method._Anyone with intermediate Python knowledge who’s interested in learning about using the Reinforcement Learning from Human Feedback technique. 

Reinforcement Learning From Human Feedback

Learn best practices for prompting and selecting among Meta Llama 2 & 3 models. Interact with Meta Llama 2 Chat, Code Llama, and Llama Guard models.

Learn best practices specific to prompting Llama 2 & 3 models. Learn best practices specific to prompting Llama 2 & 3 models.Interact with Meta Llama 2 Chat, Code Llama, and Llama Guard models. Interact with Meta Llama 2 Chat, Code Llama, and Llama Guard models.See how you can build safe, responsible AI applications using the Llama Guard model. See how you can build safe, responsible AI applications using the Llama Guard model._Open up your prompt engineering to the Llama 2 & 3 collection of models! Learn best practices for prompting and building applications with these powerful open commercial license models.Interact with the Llama 2 and Llama 3 models with a simple API call, and explore the differences in output between models for a variety of tasks.What you’ll do: Learn best practices for prompting and selecting among the Llama 2 & 3 models by using them as a personal assistant to help you complete day-to-day tasks.Experiment with advanced prompt engineering techniques, like few-shot prompting to get Llama 2 to classify the sentiment of text messages, and chain-of-thought prompting to solve logic problems.Treat Code Llama as a pair programming partner to both learn to write and improve code.Promote safe and responsible use of LLMs by having Llama Guard check user prompts and model responses for harmful content.Llama 2 and Llama 3 models and model weights are free to download, including quantized model versions that can run on your local machine. Join a thriving community of open source developers that is building applications powered by Llama 2 and Llama 3._Anyone who is interested in learning prompt engineering and wants to try out Meta Llama 2 and Llama 3 models.

Prompt Engineering with Llama 2&3

Learn how to easily build AI applications using open-source models and Hugging Face tools. Find and filter open-source models on Hugging Face Hub.

Find and filter open source models on Hugging Face Hub based on task, rankings, and memory requirements. Find and filter open source models on Hugging Face Hub based on task, rankings, and memory requirements.Write just a few lines of code using the transformers library to perform text, audio, image, and multimodal tasks. Write just a few lines of code using the transformers library to perform text, audio, image, and multimodal tasks.Easily share your AI apps with a user-friendly interface or via API and run them on the cloud using Gradio and Hugging Face Spaces. Easily share your AI apps with a user-friendly interface or via API and run them on the cloud using Gradio and Hugging Face Spaces._The availability of models and their weights for anyone to download enables a broader range of developers to innovate and create.In this course, you’ll select open source models from Hugging Face Hub to perform NLP, audio, image and multimodal tasks using the Hugging Face transformers library. Easily package your code into a user-friendly app that you can run on the cloud using Gradio and Hugging Face Spaces.You will:Use the transformers library to turn a small language model into a chatbot capable of multi-turn conversations to answer follow-up questions.Translate between languages, summarize documents, and measure the similarity between two pieces of text, which can be used for search and retrieval.Convert audio to text with Automatic Speech Recognition (ASR), and convert text to audio using Text to Speech (TTS).Perform zero-shot audio classification, to classify audio without fine-tuning the model.Generate an audio narration describing an image by combining object detection and text-to-speech models.  Identify objects or regions in an image by prompting a zero-shot image segmentation model with points to identify the object that you want to select.Implement visual question answering, image search, image captioning and other multimodal tasks.Share your AI app using Gradio and Hugging Face Spaces to run your applications in a user-friendly interface on the cloud or as an API. The course will provide you with the building blocks that you can combine into a pipeline to build your AI-enabled applications!_Anyone who wants to get started building AI applications quickly and easily using open source models.

Open Source Models with Hugging Face

Understand how LLMs predict the next token and how techniques like KV caching can speed up text generation. Write code to serve LLM applications efficiently to multiple users.

Learn how Large Language Models (LLMs) repeatedly predict the next token, and how techniques like KV caching can greatly speed up text generation. Learn how Large Language Models (LLMs) repeatedly predict the next token, and how techniques like KV caching can greatly speed up text generation.Write code to efficiently serve LLM applications to a large number of users, and examine the tradeoffs between quickly returning the output of the model and serving many users at once. Write code to efficiently serve LLM applications to a large number of users, and examine the tradeoffs between quickly returning the output of the model and serving many users at once.Explore the fundamentals of  Low Rank Adapters (LoRA) and see how Predibase builds their LoRAX framework inference server to serve multiple fine-tuned models at once. Explore the fundamentals of Low Rank Adapters (LoRA) and see how Predibase builds their LoRAX framework inference server to serve multiple fine-tuned models at once._Join our new short course, Efficiently Serving Large Language Models, to build a ground-up understanding of how to serve LLM applications from Travis Addair, CTO at Predibase. Whether you’re ready to launch your own application or just getting started building it, the topics you’ll explore in this course will deepen your foundational knowledge of how LLMs work, and help you better understand the performance trade-offs you must consider when building LLM applications that will serve large numbers of users.You’ll walk through the most important optimizations that allow LLM vendors to efficiently serve models to many customers, including strategies for working with multiple fine-tuned models at once. In this course, you will:Learn how auto-regressive large language models generate text one token at a timeImplement the foundational elements of a modern LLM inference stack in code, including KV caching, continuous batching, and model quantization, and benchmark their impacts on inference throughput and latency.Explore the details of how LoRA adapters work, and learn how batching techniques allow different LoRA adapters to be served to multiple customers simultaneously.Get hands-on with Predibase’s LoRAX framework inference server to see these optimization techniques implemented in a real world LLM inference server.Knowing more about how LLM servers operate under the hood will greatly enhance your understanding of the options you have to increase the performance and efficiency of your LLM-powered applications._Anyone who wants to understand the components, techniques, and tradeoffs of efficiently serving LLM applications, and gain a step-by-step understanding of how they work. This course relies on intermediate Python knowledge and demonstrates real-world techniques and applications.

Efficiently Serving LLMs

Learn how to quantize any open-source model. Learn to compress models with the Hugging Face Transformers library and the Quanto library.

Learn how to compress models with the Hugging Face Transformers library and the Quanto library. Learn how to compress models with the Hugging Face Transformers library and the Quanto library.Learn about linear quantization, a simple yet effective method for compressing models. Learn about linear quantization, a simple yet effective method for compressing models.Practice quantizing open source multimodal and language models. Practice quantizing open source multimodal and language models._Generative AI models, like large language models, often exceed the capabilities of consumer-grade hardware and are expensive to run. Compressing models through methods such as quantization makes them more efficient, faster, and accessible. This allows them to run on a wide variety of devices, including smartphones, personal computers, and edge devices, and minimizes performance degradation.Join this course to:Quantize any open source model with linear quantization using the Quanto library.Get an overview of how linear quantization is implemented. This form of quantization can be applied to compress any model, including LLMs, vision models, etc.Apply “downcasting,” another form of quantization, with the Transformers library, which enables you to load models in about half their normal size in the BFloat16 data type.By the end of this course, you will have a foundation in quantization techniques and be able to apply them to compress and optimize your own generative AI models, making them more accessible and efficient._This is an introduction to the fundamental concepts of quantization for learners with a basic understanding of machine learning concepts and some experience with PyTorch, who is interested in learning about model quantization in generative AI. 

Quantization Fundamentals with Hugging Face

Understand the transformer architecture that powers LLMs to use them more effectively.

Gain an understanding of the key components of transformers, including tokenization, embeddings, self-attention, and transformer blocks, to build a strong technical foundation. Gain an understanding of the key components of transformers, including tokenization, embeddings, self-attention, and transformer blocks, to build a strong technical foundation.Understand recent transformer improvements to the attention mechanism such as KV cache, multi-query attention, grouped query attention, and sparse attention. Understand recent transformer improvements to the attention mechanism such as KV cache, multi-query attention, grouped query attention, and sparse attention.Compare tokenization strategies used in modern LLMS and explore transformers in the Hugging Face Transformers library. Compare tokenization strategies used in modern LLMS and explore transformers in the Hugging Face Transformers library._Introducing “How Transformer LLMs Work,” created with Jay Alammar and Maarten Grootendorst, authors of the “Hands-On Large Language Models” book. This course offers a deep dive into the main components of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI. In fact, the “GPT” in ChatGPT stands for “Generative Pre-Trained Transformer.” Originally introduced in the groundbreaking 2017 paper Attention Is All You Need, by Ashish Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, and Anthropic.In their book, Jay and Maarten beautifully illustrated the underlying architecture of LLMs through insightful and easy-to-understand explanations.In this course, you’ll learn how a transformer network architecture that powers LLMs works. You’ll build the intuition of how LLMs process text and work with code examples that illustrate the key components of the transformer architecture.Key topics covered in this course include:The evolution of how language has been represented numerically, from the Bag-of-Words model through Word2Vec embeddings to the transformer architecture that captures word meanings in full context.How LLM inputs are broken down into tokens, which represent words or pieces before they are sent to the language model.The details of a transformer and the three main stages, consisting of tokenization and embedding, the stack of transformer blocks, and the language model head.The details of the transformer block, including attention, which calculates relevance scores followed by the feedforward layer, which incorporates stored information learned in training.How cached calculations make transformers faster, how the transformer block has evolved over the years since the original paper was released, and how they continue to be widely used.Explore an implementation of recent models in the Hugging Face transformer library.By the end of this course,  you’ll have a deep understanding of how LLMs process language and you’ll be able to read through papers describing models and understand the details that are used to describe these architectures. This intuition will help improve your approach to building  LLM applications._Anyone interested in understanding the inner workings of transformer architectures that power today’s LLMs.