GGayatri Panse·Oct 31Epoch 2: It Serves. Does It Train?Fine-tuning Gemma 4 with Unsloth on two AMD Radeon RX 7900 XTX cards, and how much of the pain was actually AMD's Slug34 min read·gradientdecent.hashnode.dev2
HHaithem Slimi·Oct 30Teaching a Small Language Model to Triage Incidents: A Beginner’s Unsloth and QLoRA TutorialA beginner-friendly Colab + Unsloth experiment in synthetic data, QLoRA, held-out evaluation, and strict schema validation.31 min read·nightthoughts.me35JKN
HHaithem Slimi·Oct 25Teaching a Small Local Model to Think in DifferentialsA DDXPlus and QLoRA experiment on Apple Silicon, from held-out evaluation to oMLX deployment31 min read·nightthoughts.me
BBusinessware Technologies·Oct 20Catalog Matching With LLMs: Why Changing Knowledge Should Stay Outside the ModelExplore how LLMs+RAG improve product catalog matching, incorporate human corrections, and reduce the need for costly model retraining and fine-tuning.10 min read·businesswaretech.hashnode.dev1A
TTaha hussein·Oct 20Fine-Tuning vs LoRA vs QLoRA: Understanding Efficient LLM AdaptationLearn how Fine-Tuning, LoRA, QLoRA, and KD-LoRA help customize AI models. Explore key differences, benefits, and LLM adaptation techniques.5 min read·tahahussein.hashnode.dev
MMuhammad Ariel Shakaramiro·Sep 25What Does Fine-Tuning Actually Learn? Testing QLoRA with Deliberately Controlled DataA controlled QLoRA experiment: format is learned first, facts come later, and brand drift turns out to just be about epoch count.7 min read·shaka-ai.hashnode.dev
MMuhammad Ariel Shakaramiro·Sep 25Fine-Tuning Llama 3.1 8B for Free on Colab: QLoRA, Unsloth, and a Compression Claim That Doesn't Hold UpHow to fine-tune Llama 3.1 8B with QLoRA on free Colab, plus a real check of a 4-bit compression claim that turns out to be wrong.7 min read·shaka-ai.hashnode.dev
NNagappan S·Sep 22Fine-Tuning vs. Prompting: When Do You Actually Need to Fine-Tune?Fine-Tuning vs Prompting: When You Actually Need It8 min read·nagspidey.hashnode.dev12M
FFeroan Mothy·Sep 17I Keep Trying to Find an Excuse to Train a ModelI want to train an AI model, but I keep searching for the perfect project first. Why I'm trying to stop overthinking it and start learning by doing.6 min read·feroan.hashnode.dev
RRahul Sai Indeevar V·Sep 16Parameter-Efficient Fine-Tuning: From LoRA to QLoRAFine-tuning Large Language Models (LLMs) used to be an option only for organizations with massive compute budgets. Full fine-tuning requires updating and storing every parameter, gradient, and optimiz10 min read·rahul-ai.hashnode.dev2
