Model Compression Courses and Certifications

MIT HAN Lab

AI Model Efficiency Toolkit (AIMET) - Lecture 25

Explore AI model efficiency techniques with Qualcomm's toolkit. Learn about adaptive rounding, autocon, and transformer quantization for optimized inference and training on resource-constrained devices.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Neural Magic

How Well Do Sparse Models Transfer? - Exploring Transfer Performance in Computer Vision and NLP

Explore sparse models' transfer performance and efficiency gains in image and language tasks, outperforming dense models even at high sparsities.

• YouTube
• 50 minutes
• On-Demand
• Free Video

Unify

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
• On-Demand
• Free Video

Unify

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
• On-Demand
• Free Video

Devoxx

Real-Time AI: Low Latency Solutions for Interactive Applications

Explore strategies for optimizing AI models in real-time applications, from model compression to edge computing, enabling faster response times while maintaining performance quality.

• YouTube
• 19 minutes
• On-Demand
• Free Video

MIT HAN Lab

LLM Post-Training Techniques - Lecture 14

Dive into advanced LLM post-training techniques and deployment strategies, exploring optimization methods and practical implementation approaches for efficient language model deployment.

• YouTube
• 1 hour 19 minutes
• On-Demand
• Free Video

tinyML

Memory Optimization Techniques for On-Device Large Language Models

Discover advanced memory optimization techniques for deploying large language models on devices with limited resources, focusing on key-value caching and dynamic compression methods.

• YouTube
• 31 minutes
• On-Demand
• Free Video

NashKnolX

Optimizing Model Performance Through Pruning

Discover how model pruning techniques enhance machine learning efficiency and speed without sacrificing accuracy, with implementation strategies and real-world performance optimization demos.

• YouTube
• 47 minutes
• On-Demand
• Free Video

Snorkel AI

Improving the Accuracy of Domain Specific Tasks with LLM Distillation

Discover how to distill large language models into smaller, efficient ones for domain-specific tasks, balancing accuracy with cost and latency through techniques like weak supervision and limited-data fine-tuning for enterprise deployment.

• YouTube
• 49 minutes
• On-Demand
• Free Video

tinyML

TinyML Talks Pakistan - SuperSlash - Unifying Design Space Exploration and Model Compression

Unifying design space exploration and model compression for efficient deep learning accelerators on resource-constrained devices, optimizing off-chip memory access and model size.

• YouTube
• 53 minutes
• On-Demand
• Free Video

Anyscale

Optimizing vLLM Performance Through Quantization - Model Compression Techniques

Discover practical techniques for model quantization in vLLM deployments, exploring FP8, INT8, and INT4 methods to enhance performance and reduce memory usage while maintaining efficiency.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Quantization for GenAI Models

95 ratings at Udemy

Unlock the power of model optimization! Learn how to apply quantization and make your GenAI models efficient with Python

• Udemy
• 2 hours 43 minutes
• On-Demand
• Paid Course

Small Language Models (SLMs): Private AI, Edge & Strategy

72 ratings at Udemy

Compare SLMs vs LLMs. Understand Offline AI, Privacy, Quantization & Pruning. Evaluate models like Llama 3 or Gemma

• Udemy
• 2 hours 44 minutes
• On-Demand
• Paid Course

Quantization Fundamentals with Hugging Face

15 ratings at Coursera

Learn to compress and optimize generative AI models through quantization techniques, making them more efficient and accessible for various devices while minimizing performance loss.

• Coursera
• 1 hour 30 minutes
• On-Demand
• Paid Course

Quantization in Depth

Build and customize linear quantization methods to compress model weights, balance performance and space tradeoffs, and implement techniques for 8-bit and 2-bit quantization in PyTorch.

• Coursera
• 1 hour 30 minutes
• On-Demand
• Paid Course