Santiago Valdarrama
Founder, Underfitted | AI Educator, Machine Learning Engineer & Content Creator
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Santiago Valdarrama. Every entry undergoes editorial source verification.
Hands-on Fine-Tuning Open Source LLMs for Production Tasks
Created open-source walkthroughs showing practitioners how to prepare structured JSONL datasets, apply LoRA adapters via Hugging Face PEFT, and quantize models using bitsandbytes on a single GPU.
Single-GPU fine-tuning restricts effective batch sizes without gradient accumulation and activation checkpointing.
From Scratch: Intuitive Vector Search & Embedding Spaces
Authored an interactive architectural breakdown explaining how high-dimensional vectors, dot-product projections, cosine similarities, and Hierarchical Navigable Small World (HNSW) graphs work under the hood.
HNSW approximate nearest neighbors algorithms trade off index build time and RAM consumption for query latency.