Tag feed

#finetuning

211 posts4 followers

Explore Hashnode

Alternatives

Trending tags this week

MAMuhammad Ariel Shakaramiroshaka-ai.hashnode.dev6d ago · 7 min read

What Does Fine-Tuning Actually Learn? Testing QLoRA with Deliberately Controlled Data

Fine-tuning is often treated as a way to "embed knowledge" into a model — but what actually happens under the hood can be far more layered than that. This post builds a small, controlled experiment —

0

MAMuhammad Ariel Shakaramiroshaka-ai.hashnode.dev6d ago · 7 min read

Fine-Tuning Llama 3.1 8B for Free on Colab: QLoRA, Unsloth, and a Compression Claim That Doesn't Hold Up

An 8-billion-parameter model usually needs tens of gigabytes of VRAM just to load, let alone retrain. But with 4-bit quantization and LoRA combined, fine-tuning a model that size can run on Colab's fr

0

NSNagappan Snagspidey.hashnode.devSep 22 · 8 min read

Fine-Tuning vs. Prompting: When Do You Actually Need to Fine-Tune?

A team I know spent two weeks and a few hundred dollars fine-tuning a model to get their internal support bot to answer in a consistent, on-brand tone. They collected examples, cleaned them up, ran th

2

M

FMFeroan Mothyferoan.hashnode.devSep 17 · 6 min read

I Keep Trying to Find an Excuse to Train a Model

I keep wanting to train a model. Then I start looking for a reason to train one. And that's where I get stuck. I can think of plenty of things I could build with an existing model. An API, a RAG syste

0

RSRahul Sai Indeevar Vrahul-ai.hashnode.devSep 16 · 10 min read

Parameter-Efficient Fine-Tuning: From LoRA to QLoRA

Fine-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 optimiz

0

PJPraise Jameszenrows.hashnode.devSep 14 · 8 min read

Web data for LLM fine-tuning: a practical 2026 guide

This article was originally published on the Zenrows blog. Read the original here: https://www.zenrows.com/blog/web-data-llm-fine-tuning Architecture overview LLM fine-tuning pipelines that rely enti

0

RSRahul Sai Indeevar Vrahul-ai.hashnode.devSep 8 · 14 min read

LLM Post-Training: From Full Fine-Tuning to PEFT, Adapters, and Soft Prompts

Large Language Models (LLMs) arrive with immense foundational knowledge acquired during pre-training. However, deploying them to specialized real-world domains—such as legal document parsing, medical

0

IDInternals Decodedinternals-decoded.hashnode.devSep 2 · 15 min read

Fine-Tuning, Explained: Teaching an Old Model New Tricks

Fine-tuning takes a pre-trained model and subjects it to a second round of training on a small, task-specific dataset. The result is a permanent behavior change: a generic chatbot learns to write in y

0

RSRahul Sai Indeevar Vrahul-ai.hashnode.devAug 28 · 9 min read

Understanding LoRA: Parameter-Efficient Fine-Tuning for Modern LLMs

Large Language Models (LLMs) and foundation models like LLaMA, GPT, and ViTs have billions of parameters. As these models scale, traditional full fine-tuning—updating every weight in the network—becom

0

VCVishal Chandakforwardstack.hashnode.devAug 22 · 17 min read

From Massive to Miniature: How Small Language Models Are Engineered

In Part 1, we started with a simple question: Does every AI task need the biggest model we can afford? Often, the answer is no. A model that is considerably smaller than a frontier model can be the

0

#finetuning

Search Hashnode

#finetuning

Explore Hashnode

Trending tags this week

What Does Fine-Tuning Actually Learn? Testing QLoRA with Deliberately Controlled Data

Fine-Tuning Llama 3.1 8B for Free on Colab: QLoRA, Unsloth, and a Compression Claim That Doesn't Hold Up

Fine-Tuning vs. Prompting: When Do You Actually Need to Fine-Tune?

I Keep Trying to Find an Excuse to Train a Model

Parameter-Efficient Fine-Tuning: From LoRA to QLoRA

Web data for LLM fine-tuning: a practical 2026 guide

LLM Post-Training: From Full Fine-Tuning to PEFT, Adapters, and Soft Prompts

Fine-Tuning, Explained: Teaching an Old Model New Tricks

Understanding LoRA: Parameter-Efficient Fine-Tuning for Modern LLMs

From Massive to Miniature: How Small Language Models Are Engineered