Thang Tran·5d agoFine-Tuning LLMs Locally on CPU with Qwen2.5 & LoRAWhen working with AI, calling third-party APIs is fast, but it strips away core control. This article summarizes the complete journey of…
Akarte Anurag·Oct 24Instruction Tuning: Teaching AI to Follow InstructionsA simple guide to what instruction tuning is, how it works, what it can and can’t do, and how to use it with your own content.
Dhirendra Choudhary·Oct 13RAG vs. Fine-Tuning vs. Just Using a Bigger Context Window: A Decision TreeThe first question isn’t “RAG or fine-tuning?” It’s ”is my problem knowledge or behavior?” Get that right and the rest of the decision…
Udi·Sep 6Nine Points, Then We TrainedWhat a fund-accounting hackathon (re)taught me about the smallest available fix — earning the right to finetune — and where that thread…
Sandeep Aggarwal·Aug 27From First LoRA Run to a Working Fine-Tune: What Actually Made the DifferenceFine-tuning a large language model with LoRA is easy to start and surprisingly easy to get wrong.
Asthamaurya·Aug 2Fine-Tuning an Open-Source LLM with Unsloth: A Hands-On WalkthroughLoading, quantizing, and teaching a model new tricks with LoRA — without needing a data-center GPU
Sherry Gong·Jul 15PolicyCompiler: Compiling Natural-Language Policies into Deterministic Guardrails with a Fine-Tuned…#NebiusServerlessChallenge
InStackademicbySandeep Singh (Full Stack Dev.)·Jul 11I Have 10 Minutes to Train an AI Model. Here’s Exactly What Happened.A few days ago I sat down, opened a terminal, and gave myself a stupid little constraint: train a real model, on a real dataset, with real…A response icon1A response icon1
Prafull R·Jun 29Why RAG still beats fine-tuning for most teams?The debate keeps treating fine-tuning as the advanced move. The data says it’s usually the wrong tool for the job teams hire it to do.
Sumanta Swain·Jun 27Build a LoRA Fine-tuning Pipeline from Scratch in 100 Lines of PythonFine-tune a 3B language model on your own data free, fast, and fully open source
