#jax (36)
- Representing Reality: From Raw Data to Embeddings
Unlock the secret behind multimodal AI: learn how raw text, image, audio, and video data are transformed into powerful numerical embeddings for AI understanding.
- UniFace Concepts: Face Biometrics
Embark on a comprehensive journey to master advanced face biometrics using UniFace concepts, from foundational principles to real-world applications and ethical considerations.
- Setting Up Your Advanced Biometrics Development Environment
Learn how to set up a robust development environment for advanced face biometrics projects, covering Python, deep learning frameworks, and essential libraries.
- Efficient LLM Post-Training with Tunix and JAX
Learn to efficiently align and refine Large Language Models using Tunix, Google's JAX-native library for post-training techniques such as SFT and RLHF.
- The World of LLM Post-Training and Tunix
Learn how to use Tunix, a JAX-native library for LLM post-training and specialization.
- Setting Up Your Tunix Environment
A step-by-step guide to setting up your Tunix environment for LLM post-training.
- JAX Essentials for Tunix Users
Learn the essentials of JAX for optimizing and diagnosing LLM training workflows in Tunix.
- Your First Supervised Fine-Tuning (SFT) Project with Tunix
Learn to perform Supervised Fine-Tuning with Tunix, preparing data, configuring the Trainer, and observing your model learn new skills.
- Prepare & Load Data for Tunix LLM: Tokenization & JAX Pipelines
Master preparing and tokenizing text datasets, then build efficient JAX data loading pipelines to optimize your Tunix Large Language Model's performance.
- Tunix LLM Architectures: Functional State Management with JAX
Understand how Tunix leverages JAX and Flax NNX to define LLM architectures and manage their explicit state for advanced post-training routines.
- RLHF: Principles for Aligning LLMs with Human Values
Reinforcement Learning from Human Feedback concepts are explained, detailing how LLMs are aligned with human values to generate helpful, harmless, and honest text.
- Implementing Basic RLHF Workflows with Tunix
Learn how to implement basic RLHF workflows with Tunix for creating helpful and aligned Language Models.
- Distributed Training and Scaling with Tunix
Learn how to scale large language models using Tunix and JAX for distributed training.
- Define Custom Loss Functions, Optimizers, and Callbacks in Tunix
Tailor Tunix for advanced LLM post-training by defining custom loss functions, crafting optimizers, and implementing intelligent callbacks.
- Build a Specialized Conversational AI with Tunix Fine-Tuning
Discover how to fine-tune a pre-trained Large Language Model with Tunix, JAX, and Flax to develop a specialized conversational partner.
- Implement PPO for Robust LLM Alignment with RLHF
Understand the core mechanics of Proximal Policy Optimization and apply it with Tunix to align large language models effectively using human feedback.
- Practical LLM Alignment for Factual Accuracy using Tunix
Learn to align a Large Language Model for factual accuracy, mastering practical techniques to reduce hallucinations and ensure reliable information delivery with Tunix.
- Diagnose and Resolve Issues in Tunix Workflows with JAX
Acquire essential tools and techniques to diagnose and resolve issues in Tunix workflows, understand JAX error messages, and leverage Tunix's built-in logging.
- Deployment Strategies for Fine-Tuned LLMs
Learn how to deploy fine-tuned LLMs using FastAPI and Docker for efficient, scalable inference.
- Integrating with ML Frameworks (PyTorch/TensorFlow)
Learn how to integrate Meta AI's dataset library with PyTorch and TensorFlow for efficient model training.
- AI/ML Engineering: A Step-by-Step Learning Path
Acquire foundational knowledge and advanced practical skills to build a thriving career in AI/ML engineering, covering core concepts and advanced applications.
- Model Training, Evaluation & Hyperparameter Tuning
Learn how to train, evaluate, and fine-tune machine learning models using PyTorch and TensorFlow Keras.
- Convolutional Neural Networks (CNNs) for Computer Vision
Learn how to build and train a CNN for image classification using TensorFlow and Keras.
- Recurrent Neural Networks (RNNs) for Sequence Data
Learn how to implement RNNs, LSTMs, and GRUs for processing sequential data using PyTorch.
- Model Training Workflows & Optimization Techniques
Learn the practical aspects of model training workflows and optimization techniques in machine learning.
- Distributed Training & Scaling Deep Learning
Learn how to scale deep learning models using distributed training with PyTorch.
- Project: Building a Custom Image Classifier
Learn to build a custom image classifier from scratch using PyTorch and transfer learning techniques.
- Project: Fine-Tuning an LLM for a Specific Task
Learn how to fine-tune a Large Language Model for a specific task using Parameter-Efficient Fine-Tuning techniques like LoRA.
- Learn TensorFlow: Build, Train, & Deploy ML Models
Learn TensorFlow from the basics to advanced concepts, enabling you to confidently build, train, and deploy machine learning models for practical applications.
- Scale TensorFlow Training and Deploy Models with TensorFlow Lite
Readers will learn to scale TensorFlow model training across multiple devices and efficiently deploy models to various environments using TensorFlow Lite.
- TensorFlow Guide: Building Your First Neural Network with Keras
Learn how to build, compile, and train your first neural network using Keras in TensorFlow.
- TensorFlow Guide: Guided Project 1 - Image Classification with CNNs
Step-by-step guide to building a CNN for CIFAR-10 image classification using TensorFlow and Keras.
- TensorFlow Guide: Guided Project 2 - Text Generation with LSTMs
Build a character-level text generation model using TensorFlow and LSTM to generate creative text based on Shakespeare's works.
- TensorFlow Core Concepts: Tensors, Operations, and Graphs
Readers will learn how TensorFlow represents data using Tensors, processes computations with Operations, and structures entire models through computation Graphs.
- TensorFlow Guide: Working with Data - `tf.data` API
Learn how to efficiently load, preprocess, and feed data to your models using TensorFlow's tf.data API.
- Control TensorFlow Training with Custom Loops and Keras Callbacks
Learn how to implement custom training loops and use callbacks in TensorFlow for more control over the training process.