Published onOctober 17, 2023Investigations into fine-tuning LLMs to be good at RAGResearch on whether fine-tuning on retrieval-augmented prompts works better than fine-tuning on zero-shot prompts
Published onSeptember 19, 2023GPT 3.5 vs Llama 2 fine-tuning: A Comprehensive ComparisonIn this guide I show you how to fine-tune Code Llama to become a beast of an SQL developer using a Lora approach
Published onSeptember 4, 2023A complete guide to fine-tuning Code LlamaIn this guide I show you how to fine-tune Code Llama to become a beast of an SQL developer using a Lora approach
Published onJune 15, 2022Training an AI AnimatorMy Master's thesis research project; building an AI animator training large autoregressive transformers on the Flintstones dataset.