Generative AI LLMs

Skills covered in this course:

• Define generative AI and explain how it works. ​
• Describe various generative AI applications. ​
• Explain the challenges and opportunities of generative AI.

You can take one of these courses:

Skills covered in these courses:

• Understand the fundamental techniques and tools required to train a deep learning model.

• Gain experience with common deep learning data types and model architectures. 
• Leverage transfer learning between models to achieve efficient results with less data and computation. 
• Take on your own project with a modern deep learning framework.

• Enhance datasets through data augmentation to improve model accuracy.

You can take one of these courses:

Skills covered in these courses:

Understand GPU-accelerated data manipulation:

• Ingest and prepare several datasets (some larger-than-memory) for use in multiple machine learning exercises.
• Read data directly to single and multiple GPUs with cuDF and Dask cuDF.
• Prepare information for machine learning tasks on the GPU with cuDF.
• Apply several essential machine learning techniques to prepared data.
• Use supervised and unsupervised GPU-accelerated algorithms with cuML.
• Train XGBoost models with Dask on multiple GPUs.
• Create and analyze graph data on the GPU with cuGraph.
• Use NVIDIA RAPIDS™ to integrate multiple massive datasets and perform analysis.
• Implement GPU-accelerated data preparation and feature extraction using cuDF and Apache Arrow data frames.
• Apply a broad spectrum of GPU-accelerated machine learning tasks using XGBoost and a variety of cuML algorithms.
• Execute GPU-accelerated graph analysis with cuGraph, achieving massive-scale analytics in small amounts of time.
• Rapidly achieve massive-scale graph analytics using cuGraph routines.

Skills covered in this course:

• Learn to describe how transformers are used as the basic building blocks of modern LLMs for natural language processing (NLP) applications.
• Understand how transformer-based LLMs can be used to manipulate, analyze, and generate text-based data.

• Leverage pretrained, modern LLMs to solve various NLP tasks such as token classification, text classification, summarization, and question-answering.

• Understand how transformer-based LLMs can be used to manipulate, analyze, and generate text-based data.  
• Leverage pretrained, modern LLMs to solve various NLP tasks such as token classification, text classification,  summarization, and question-answering.

• Understand how transformer-based LLMs can be used to manipulate, analyze, and generate text-based data.

Skills covered in this course:

• Know how transformers are used as the basic building blocks of modern LLMs for natural language processing (NLP) applications. 
•  Know how self-supervision improves upon the transformer architecture in BERT, Megatron, and other LLM variants for superior NLP results.

• Apply self-supervised transformer-based models to concrete NLP tasks using NVIDIA NeMo™. 
• Deploy an NLP project for live inference on NVIDIA Triton™. 
• Manage inference challenges and deploy refined models for live applications.

• Leverage pretrained, modern LLM models to solve multiple NLP tasks such as text classification, named-entity recognition (NER), and  question-answering.

Skills covered in this course:

•  Iteratively write precise prompts to bring LLM behavior in line with your intentions.

• Leverage editing the powerful system message.  
• Guide LLMs with one-to-many-shot prompt engineering.  
• Incorporate prompt-response history into the LLM context to create chatbot behavior.

Skills covered in this course:

• Understand the basics of retrieval-augmented generation (RAG).  
• Understand the RAG process.  
• Be familiar with NVIDIA AI Foundation models and the components that constitute a RAG model.

Skills covered in this course:

• Explore scalable deployment strategies for LLMs and vector databases. 
• Practice with state-of-the-art models with clear next steps regarding productionalization and  framework exploration.

• Understand microservices—how to work between them and how to develop your own. 
• Practice with state-of-the-art models with clear next steps regarding productionalization and framework exploration.

• Experiment with modern LangChain paradigms to develop dialog management and document-retrieval solutions.

• Practice with state-of-the-art models with clear next steps regarding productionalization and framework exploration.

Skills covered in this course:

• Find, pull in, and experiment with the Hugging Face model repository and the associated transformers API.
• Use state management and composition techniques to guide LLMs for safe, effective, and accurate conversation.

• Find, pull in, and experiment with the Hugging Face model repository and the associated transformers API. 
• Use encoder models for tasks like semantic analysis, embedding, question-answering, and zero-shot classification. 
• Use decoder models to generate sequences like code, unbounded answers, and conversations. 
• Use state management and composition techniques to guide LLMs for safe, effective, and accurate conversation.

• Use state management and composition techniques to guide LLMs for safe, effective, and accurate  conversation.

Skills covered in this course:

• Understand content authenticity and how to build trustworthy models.

Skills covered in this course:

• Know how to apply fine-tuning techniques.
• Understand how to effectively integrate and interpret diverse data types within a single-model framework.

• Leverage the NVIDIA NeMo™ framework to customize models like GPT, LLaMA-2, and Falcon with ease.

• Use prompt engineering to improve the performance of pretrained LLMs. 
• Apply various fine-tuning techniques.

• Assess the performance of fine-tuned models.