Tag: embeddings

Mar 29, 2026 · Ruby Jha · project-deep-dives
LoRA Hit 96% of Full Fine-Tuning. The Default Learning Rate Almost Killed It.
I fine-tuned all-MiniLM-L6-v2 on dating profiles, flipped Spearman from -0.22 to +0.85, and found LoRA hit 96.2% of that with 0.32% of parameters.
Mar 21, 2026 · Ruby Jha · project-deep-dives
I Tested 16 RAG Configs So You Don't Have To: Embedding Choice Matters More Than Chunk Size
Grid search across 16 RAG configurations reveals embedding model selection drives 26% more retrieval quality than chunk tuning.