Build LLM apps that can process very long documents using the Jamba model

Learn how the Jamba model integrates transformers and the Mamba architecture to efficiently process long contexts while maintaining quality. Learn how the Jamba model integrates transformers and the Mamba architecture to efficiently process long contexts while maintaining quality.Understand the training process for long context models, and the metrics used to evaluate their performance. Understand the training process for long context models, and the metrics used to evaluate their performance.Gain hands-on experience applying Jamba to tasks such as processing large documents, tool-calling, and building large context RAG apps. Gain hands-on experience applying Jamba to tasks such as processing large documents, tool-calling, and building large context RAG apps._Learn to use the Jamba model, a hybrid transformer-Mamba architecture trained to handle long contexts, in this new course, Build Long-Context AI Apps with Jamba, built in partnership with AI21 Labs and taught by Chen Wang and Chen Almagor.The transformer architecture is the foundation of most large language models but it is computationally expensive when handling very long input contexts. There’s an alternative to transformers called Mamba. Mamba is a selective state space model that can process very long contexts with a much lower computational cost. However, researchers found that the pure Mamba architecture underperforms in understanding the context, and the quality of the output can be lower even in tasks as simple as repeating the input in the output of the model.To overcome these challenges, AI21 Labs developed the Jamba model, which combines Mamba’s computational efficiency with the transformer’s attention mechanism to help with the output quality.In this course, you’ll learn about the Jamba architecture, how it works, and how it is trained. You’ll also learn how to prompt Jamba and use it to process long documents and build long-context RAG apps.In detail, you’ll:Learn key information about Jamba’s large context model and its unique, hybrid architecture that allows for high-quality outputs, high throughput, and low memory usage.Learn how Jamba combines transformers with Mamba, a selective state-space model to achieve high performance and quality.Use the AI21SDK, especially its document parameter, with an example of prompting a large over 200k-token annual report.Use Jamba for tool-calling with hands-on examples from calling simple arithmetic functions to a function that returns SEC 10-Q company quarterly report.Learn how the training for long context is done, and the metrics used for evaluating the performance.Create a RAG app using the AI21 Conversational RAG tool and build your own RAG pipeline that uses the Jamba model with LangChain.Start building AI apps that can handle context as long as all of your unread emails from the last 20 years!_Anyone who has basic Python knowledge and wants to learn more about how the Jamba model works and how it is used for building long-context AI apps.

Build Long-Context AI Apps with Jamba

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

Move your LLM-powered applications beyond proof-of-concept and into production with the added control of guardrails.

Learn the common failure modes of LLM-powered applications that guardrails can help mitigate, including hallucinations and revealing sensitive information. Learn the common failure modes of LLM-powered applications that guardrails can help mitigate, including hallucinations and revealing sensitive information.Understand how AI guardrails validate and verify your applications with input and output guards, ensuring reliable and controlled interactions. Understand how AI guardrails validate and verify your applications with input and output guards, ensuring reliable and controlled interactions.Add guardrails to a RAG-powered customer service chatbot to create a new layer of control of the applications behavior. Add guardrails to a RAG-powered customer service chatbot to create a new layer of control of the applications behavior._Join our new short course, Safe and Reliable AI via Guardrails, and learn how to build production-ready applications with Shreya Rajpal, co-founder & CEO of GuardrailsAI.The output of LLMs is fundamentally probabilistic, making it impossible to know in advance, or to guarantee the same response twice. This makes it difficult to put LLM-powered applications into production for industries with strict regulations or clients who require high consistency in application behavior. Fortunately, installing guardrails on your system gives you an additional layer of control in creating safe and reliable applications. Guardrails are safety mechanisms and validation tools built into AI applications, acting as a protective framework that prevents your application from revealing incorrect, irrelevant, or sensitive information. This course will show you how to build robust guardrails from scratch that mitigate common failure modes of LLM-powered applications like hallucinations or revealing personally identifiable information (PII). You’ll also learn how to access a variety of pre-built guardrails on the GuardrailsAI hub and are ready to integrate into your projects.You’ll implement these guardrails in the context of a RAG-powered customer service chatbot for a small pizzeria.In detail, you’ll: Explore the common failure modes of LLM-powered applications including hallucinations, going off-topic, revealing sensitive information, and generating responses that can harm your reputation.Learn to mitigate these failure modes with input and output guards that validate and verify your application’s responses.Create a guardrail to prevent the chatbot from discussing sensitive topics, such as a confidential project at the pizza shop.Develop a guardrail to detect hallucinations using a Natural Language Inference (NLI) model, ensuring responses are grounded in the truth of your trusted documents.Add a Personal Identifiable Information (PII) guardrail to detect and redact sensitive information in user prompts and LLM outputs using tools from the Guardrails hub.Set up a guardrail to limit the chatbot’s responses to topics relevant to the pizza shop, keeping interactions focused and appropriate.Configure a guardrail that prevents your chatbot from mentioning any competitors using a name detection pipeline consisting of conditional logic that routes to an exact match or a threshold check with a named entity recognition.The tools in this course will unlock more opportunities for you to build and deploy safe, reliable LLM-powered applications ready for real-world use._Anyone who has basic Python knowledge looking to enhance the safety and reliability of LLM-powered applications with practical, hands-on guardrail techniques.

Safe and reliable AI via guardrails

Learn to use OpenAI Canvas to write, code, and create more effectively in collaboration with AI.

Learn to write and code more effectively with OpenAI Canvas, using features like targeted editing, in-line feedback, changing the reading level, final polish, reviewing code, and fixing bugs. Learn to write and code more effectively with OpenAI Canvas, using features like targeted editing, in-line feedback, changing the reading level, final polish, reviewing code, and fixing bugs.Learn how to build practical use cases like creating a game app, generating Python code from plot screenshots, and creating SQL databases from architecture images. Learn how to build practical use cases like creating a game app, generating Python code from plot screenshots, and creating SQL databases from architecture images.Gain knowledge of how GPT-4o was trained to bring the OpenAI Canvas features and functionalities to life. Gain knowledge of how GPT-4o was trained to bring the OpenAI Canvas features and functionalities to life._Explore a new way to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course Collaborative Writing and Coding with OpenAI Canvas, taught by Karina Nguyen, research lead at OpenAI, you’ll learn how to use this tool to enhance your writing and coding.Canvas provides a side-by-side workspace where you and ChatGPT can collaboratively edit and refine text or code. This makes brainstorming, drafting, and iterating on the text feel more natural and effective.For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logs, identifying problems to fix, and writing comments for your code.This course will teach you how to make the most of the new interactive Canvas workspace and tools to make your writing more flexible, more efficient, and a lot more fun as you go behind the scenes with examples of the different use cases and learn what it takes to train the model to powers Canvas’s features and functionalities.In this video-only short course, you’ll:Learn how to ask for in-line feedback and control the iteration of your creative work by directly editing selected areas of your text or code from the model’s output.Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work.Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the report.Extend its use case by asking the model to write Python code to replicate the graph seen on a screenshot image.Go behind the scenes of how you can create a video game such as Space Battleship from scratch, edit it, and display it in one self-contained HTML file.Get a real-world application example of creating a SQL database from the image of its architecture.Understand the model training and design processes that power Canvas.By the end of this course, you’ll learn about all the possibilities that the new Canvas interface can bring to your writing and coding workflow._Anyone who wants to learn how to use the new OpenAI Canvas interface to write and code better.

Collaborative Writing and Coding with OpenAI Canvas

Learn how to use and prompt OpenAI's o1 model for complex reasoning tasks.

Learn about o1, what makes it work, how it performs, and the best scenarios to use it. Learn about o1, what makes it work, how it performs, and the best scenarios to use it.Learn how to prompt o1 effectively and when to delegate tasks to more cost-efficient, lower latency models. Learn how to prompt o1 effectively and when to delegate tasks to more cost-efficient, lower latency models.Learn how o1 outperforms on coding and vision reasoning tasks, and how to apply meta-prompting to optimize your applications. Learn how o1 outperforms on coding and vision reasoning tasks, and how to apply meta-prompting to optimize your applications._Learn how to effectively prompt and use OpenAI’s o1 model in Reasoning with o1, a short course built in collaboration with OpenAI and taught by Colin Jarvis, Head of AI Solutions at OpenAI.The o1 model is exceptionally good at abstract reasoning tasks. It has record-breaking performance on tasks such as planning, coding, analyzing, domain-specific reasoning like law, and other STEM subjects.In this course, you will learn how OpenAI utilized reinforcement learning to produce a model that uses ‘test-time compute’ to improve performance on many reasoning tasks. Learn what ‘chain-of-thought’ prompting is and how o1 autonomously utilizes it to break problems into smaller steps, try multiple strategies, and think through responses before returning them.In detail, you’ll: Learn to recognize what tasks the o1 model is suited for and when you might want to use a smaller or faster model or combine those two.Understand four key principles of prompting using o1 from “simple and direct” to “show rather than tell,” and explore the difference in performance.Implement a multi-step task in which o1 acts as an orchestrator creating a plan and handing it over to the 4o-mini model to execute the plan in sequence, balancing the trade-off between intelligence and cost.Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o.Use o1 for image understanding and learn how it performs better with a hierarchy of reasoning, in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later.Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you iteratively use o1 to modify a prompt to improve performance.Start building applications that require complex reasoning with o1._It’s helpful to be familiar with Python and have a basic understanding of LLM prompting and LLM application development.