AI/ML Techniques

Training a Model on Multiple GPUs with Data Parallelism

This article is divided into two parts; they are: • Data Parallelism • Distributed Data Parallelism If you have multiple…

1 month ago

Train a Model Faster with torch.compile and Gradient Accumulation

This article is divided into two parts; they are: • Using `torch.

1 month ago

Training a Model with Limited Memory using Mixed Precision and Gradient Checkpointing

This article is divided into three parts; they are: • Floating-point Numbers • Automatic Mixed Precision Training • Gradient Checkpointing…

1 month ago

Practical Agentic Coding with Google Jules

If you have an interest in agentic coding, there's a pretty good chance you've heard of

1 month ago

Evaluating Perplexity on Language Models

This article is divided into two parts; they are: • What Is Perplexity and How to Compute It • Evaluate…

1 month ago

3 Smart Ways to Encode Categorical Features for Machine Learning

If you spend any time working with real-world data, you quickly realize that not everything comes in neat, clean numbers.

1 month ago

Pretraining a Llama Model on Your Local GPU

This article is divided into three parts; they are: • Training a Tokenizer with Special Tokens • Preparing the Training…

1 month ago

Rotary Position Embeddings for Long Context Length

This article is divided into two parts; they are: • Simple RoPE • RoPE for Long Context Length Compared to…

1 month ago

5 Agentic Coding Tips & Tricks

Agentic coding only feels "smart" when it ships correct diffs, passes tests, and leaves a paper trail you can trust.

1 month ago

How to Fine-Tune a Local Mistral or Llama 3 Model on Your Own Dataset

Large language models (LLMs) like Mistral 7B and Llama 3 8B have shaken the AI field, but their broad nature…

1 month ago