LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch
Similar Tracks
Attention is all you need (Transformer) - Model explanation (including math), Inference and Training
Umar Jamil
LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU
Umar Jamil
ML Interpretability: feature visualization, adversarial example, interp. for language models
Umar Jamil
Coding LLaMA 2 from scratch in PyTorch - KV Cache, Grouped Query Attention, Rotary PE, RMSNorm
Umar Jamil