Unify Courses

Influential Data Retrieval Explained

Explore RapidIn, a scalable framework for estimating training data influence in large language models. Learn about token-wise retrieval and its two-stage approach.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Complex Agentic RAG Systems - Overcoming Limitations of Traditional RAG

Explore advanced agentic RAG systems with expert Atita Arora, overcoming traditional limitations and revolutionizing information retrieval for AI and machine learning applications.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Unify and Baseten - Boosting LLM Deployment

Supercharge LLM deployment by integrating Baseten model endpoints into Unify Platform. Learn dynamic routing, open-source model usage, and practical demonstrations for optimized AI workflows.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

YOCO: Decoder-Decoder Architectures for Language Models Explained

Explore YOCO, a decoder-decoder architecture for LLMs that improves inference memory, prefill latency, and throughput by caching key-value pairs once across context lengths and model sizes.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

Towards Monosemanticity: Decomposing Language Models with Dictionary Learning

Explore monosemanticity in neural networks through sparse autoencoders. Learn how extracting interpretable features enhances understanding of language model behavior and improves reasoning capabilities.

• YouTube
• 1 hour 10 minutes
• Self-Paced
• Free Video

ReFT: Representation Finetuning for Language Models Explained

Explore ReFT, a novel approach to fine-tuning language models by modifying internal representations, achieving efficiency with fewer parameters than traditional methods.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Explore LayerSkip, an LLM acceleration method that speeds up inference by strategically restricting model layers, achieving 2x speed-ups on various tasks through innovative techniques.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

DSPy Explained - Compiling Declarative Language Model Calls into Self-Improving Pipelines

Explore DSPy, a programming model for LM pipelines that enables self-improving AI systems through declarative modules and computational graphs. Learn its potential to enhance AI performance.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

MiniLLM: Knowledge Distillation of Large Language Models

Explore knowledge distillation techniques for large language models, focusing on reverse KLD to improve student model precision and response quality.

• YouTube
• 52 minutes
• Self-Paced
• Free Video

Building a Chatbot with Unify - Webinar 01

Learn to build an interactive ChatBot using Unify, exploring Synchronous and Asynchronous clients and integrating with various LLMs for dynamic AI conversations.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

The Era of 1-bit LLMs Explained - BitNet b1.58 and New Scaling Laws

Explore groundbreaking research on BitNet b1.58, a ternary parameter model matching full-precision Transformers while offering improved cost-effectiveness and defining new LLM scaling laws.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

SparQ Attention: Bandwidth-Efficient LLM Inference

Explore SparQ Attention, a technique for increasing LLM inference throughput by reducing memory bandwidth in attention blocks through selective history fetching, applicable to off-the-shelf models without retraining.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Explore OpenMoE, an open-source Mixture-of-Experts language model series. Discover its cost-effectiveness, routing mechanisms, and key insights in comparison to dense LLMs.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Teacher-Student Architecture for Knowledge Distillation Explained

Explore Teacher-Student architectures in knowledge distillation for AI model compression, expansion, adaptation, and enhancement. Gain insights into cutting-edge research and practical applications.

• YouTube
• 1 hour 6 minutes
• Self-Paced
• Free Video

SliceGPT Explained - Compressing Large Language Models

Explore SliceGPT's innovative approach to compressing large language models by deleting rows and columns, maintaining high performance while reducing parameters significantly.

• YouTube
• 55 minutes
• Self-Paced
• Free Video