Claudia Yao·Oct 25End-to-End LoRA Fine-Tuning: A Step-by-Step Guide and Performance Comparison of PEFT vs. UnslothPreviously, I mainly worked on computer vision models and fine-tuning, with little experience in fine-tuning language models.
Grace Esther S.·Sep 17LoRA vs QLoRA vs Prefix Tuning: Which PEFT Method Actually Wins?A practical comparison of three fine-tuning strategies, and what the numbers really mean for deployment
MOHAN MAHESH BOGGAVARAPU·Sep 8Parameter-Efficient Fine-Tuning (PEFT/LoRA) on Vertex AI (With Real Code Example) Folks in Cloud AI…Welcome back to Sprint 2 of Folks in Cloud AI! Last week, we explored how to host open-weights foundation models on Vertex AI Model Garden…
Ephrame Amanu·Aug 14PEFT Explained: How to Fine-Tune Giant Models Without Melting Your GPUIf you’ve ever tried to fine-tune a large language model on your own hardware, you already know the punchline: it hurts. A…
Akash Chandrasekar·Aug 13I Thought Fine-Tuning Was the Starting Point. Turns Out, I Was Missing the Whole Story.Understanding the LLM training pipeline, why fine-tuning exists, and where techniques like SFT, LoRA, QLoRA, and RLHF actually fit.A response icon1A response icon1
Vardhini Sirla·Aug 7What Is LoRA and Why Should You Care?You want to teach an AI model something new. Maybe you want it to understand medical text, or legal documents, or in my case financial…
YouShin kim·Aug 5Google DeepMind — 텍스트와 가중치를 동시에 읽는 AI: 파라미터 스킬 합성 모델 ‘SkillSmith’1. 한눈에 보는 핵심 요약 (Executive Summary)
Manikandan Ganesan·Jul 27From Deep Learning to Fine-Tuning LLMs: A Practical Guide for Software EngineersA few years ago, asking a computer to write code, summarize a 100-page document, answer complex questions, or explain quantum physics…
Afra·Jul 25PEFT Explained: The Smart Way to Fine-Tune Large Language ModelsHow can we fine-tune billion-parameter models without training billions of parameters? The answer lies in Parameter-Efficient Fine-Tuning…A response icon1A response icon1
VRUNDA SHAH·Jul 23Fine-Tuning LLMs: LoRA, PEFT and Domain-Specific AdaptationA practical guide to efficient LLM adaptationA response icon10A response icon10
