2026-01-20
Quantizing Your Own Fine-Tuned Model with llama.cpp
Machine Learning
2026-01-05
How LLM Quantization Actually Works
2025-12-05
Reward Modeling: Scoring LLM Outputs
2025-11-26
Merging LoRA Adapters and Serving Locally
2025-11-13
Teaching a Small LLM to Prefer JSON Over Prose
2025-11-01
Fine-Tuning a Small LLM from Scratch with LoRA
2025-10-31
Why I Write These Posts
General
Pouya (Reza) Rostam
Applied Scientist | LLMs, Fine-tuning & ML Systems
Vancouver, BC, Canada
Posts
7
Categories
2
Tags
10
