Unboxing LLMs > loading...

Articles on Tech/AI/ML/LLMs

N-shot: Few Examples, Deep Insights.

Exploring Intelligence Through Language and Learning

LLMs. Code. Theory. Clarity.

Thinking in Tokens: Essays on Language and Intelligence

Navigating the LLM Revolution, One Shot at a Time

November 30, 2024
Pause Tokens for Transformers: Making Language Models *Pretend* to Think Before Speaking
November 2, 2024
Uncovering Mesa-Optimization in Transformers
August 12, 2024
Evaluating the Evaluators: A Comprehensive Guide to LLM Benchmarks and Assessment Frameworks
June 29, 2024
Mamba: Linear-Time Sequence Modeling Beyond Transformers
May 28, 2024
Scaling Context Length in Large Language Models: Techniques and Challenges
April 26, 2024
The AI Engineer’s Toolkit: Emerging Tools, Libraries, and Frameworks in 2023-2024
April 25, 2024
Securing Large Language Models: Key Threats and Defensive Strategies
April 18, 2024
From CUDA to Triton: The Evolution of the AI Software Stack
April 5, 2024
Model Merging: Combining LLM Fine-Tunings with ZipLoRA and MergeKit
April 5, 2024
Why NVIDIA Rules: Decoding the GPU Monopoly in AI/ML
March 10, 2024
Advanced Concepts in LLM Development: Practical Tips & Implementation Insights
March 5, 2024
Reversible Layers in Transformers: Memory-Efficient Deep Learning
February 20, 2024
In-Context Learning: The Hidden Superpower of Large Language Models
February 5, 2024
Sparse Attention in Transformers: Scaling Sequence Modeling Beyond Brute Force
January 30, 2024
Proxy Tuning: A Lightweight Decoding-Time Tuning Method for Large Language Models
January 23, 2024
FunSearch: Harnessing LLM Creativity Through Evaluation Loops
January 21, 2024
The Confusion Matrix Explained: Making Sense of Classification Metrics
January 18, 2024
The Evolving Landscape of Large Language Models: A 2023 Survey
December 16, 2023
Text-to-Image Generation: From Evaluation Metrics to State-of-the-Art Models
December 15, 2023
Training Nuances in Large Language Models: Balancing Scale, Efficiency, and Performance
December 13, 2023
Mixture of Experts (MoE): Scaling AI with Intelligent Specialization
December 10, 2023
Beyond Simple Prompts: Advanced Reasoning Techniques for Large Language Models
December 8, 2023
OPRO Framework: Optimization by PROmpting
November 29, 2023
Mastering GPU Memory Constraints for Large-Scale Model Training
November 29, 2023
Demystifying Perplexity: A Core Measure of Language Model Performance
November 25, 2023
Running LLMs Locally: The Power of llama.cpp and Cosmopolitan libc
November 23, 2023
Vector Databases: Powering Semantic Search and Modern AI Retrieval
November 20, 2023
AI Data and Legal Considerations: Navigating the Complex Landscape
November 18, 2023
Energy-Based Models (EBMs): Unifying Self-Supervised Learning Through Scalar Energy Functions
November 15, 2023
Mastering LLM Inference: From Mechanics to Optimization
November 15, 2023
Diffusion Models in AI Image Generation – Part 2: Applications & Advancements
November 13, 2023
Prompt2Model: Transforming Natural-Language Prompts into Specialized Models
November 11, 2023
Diffusion Models in AI Image Generation – Part 1: Foundations
October 28, 2023
Beyond GPT: Exploring The Frontier of Large Language Models
October 26, 2023
Wanda: A Simple Yet Powerful Approach to Pruning Large Language Models
October 23, 2023
The AI Tooling Landscape: A Comprehensive Guide for Practitioners
October 22, 2023
Understanding Transformer Architectures: BERT vs. GPT
October 21, 2023
Cognitive Architectures for Language Agents (CoALA): Building Robust AI Systems
October 19, 2023
Graph of Thoughts: Solving Complex Problems with Large Language Models
October 17, 2023
Quantization in Deep Learning: Shrinking Models Without Sacrificing (Too Much) Performance
October 15, 2023
Factually-Augmented RLHF: How LLaVA Advances Multimodal Alignment
October 9, 2023
Breaking Through the Memory Wall: The Critical Bottleneck in Modern AI Training
October 3, 2023
RLAIF: Beyond RLHF – Reinforcement Learning from AI Feedback
September 23, 2023
From GPT to ChatGPT: The Magic of RLHF
September 18, 2023
Joint Embedding Predictive Architecture (JEPA): An Advanced Framework for Efficient AI Prediction and Decision-Making
September 16, 2023
Notes on Evolution of Language Models: Llama 2, Open Source, and the Future of Tokenization
September 13, 2023
QLoRA: Making Large Language Model Fine-Tuning Accessible
September 11, 2023
Parameter-Efficient Fine-Tuning: Revolutionizing LLM Adaptation
September 5, 2023
Generative Agents: Building a Virtual Smallville with AI Citizens
August 22, 2023
ZeRO: The Zero Redundancy Optimizer Revolutionizing Large-Scale Model Training
August 15, 2023
The Journey to Super Alignment: From Weak to Strong Generalization in Large Language Models
August 12, 2023
Large-Scale AI Infrastructure on Kubernetes: Scaling Training for Modern LLMs
August 3, 2023
FlashAttention: Revolutionizing Transformer Efficiency
August 1, 2023
Understanding the Transformer Architecture: Self-Attention and Beyond
July 25, 2023
The Quantization Model of Neural Scaling: Explaining Emergent Abilities in LLMs
July 17, 2023
Training Compute-Optimal Large Language Models: The Chinchilla Paradigm
July 15, 2023
The Evolution of Language Models: From Transformers to Modern AI
July 3, 2023
Activation Checkpointing: Trading Computation for Memory in Deep Learning
July 2, 2023
Vision Transformers: When Code Realized an Image is Just 16×16 Words