Tag feed

#finetuning

205 posts4 followers

Explore Hashnode

Alternatives

Trending tags this week

RSRahul Sai Indeevar Vrahul-ai.hashnode.dev3d ago · 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

DSDarsh Shahfreecodecamp.orgAug 6 · 16 min read

How to Customize an LLM for AI Agents using SFT and QLoRA

In this tutorial, I’ll show you how to fine-tune a large language model for use in AI agents using supervised fine-tuning with QLoRA. This lets us customize a pre-trained model so it behaves the way w

0

AJAman Jaincurious-pm.hashnode.devJul 21 · 7 min read

Comparing Fine-Tuning Strategies: Which Parts of a GPT Model Should We Update?

TL;DR I compared four ways of fine-tuning a small GPT model for SMS spam classification: Train only the classification head Train the final transformer block Train the final half of the transformer

0

Mmatthewtruong81matthew-codes.hashnode.devJul 8 · 6 min read

RAG or Fine-Tuning? An AI Development Services Comparison

Quick answer: RAG (Retrieval-Augmented Generation) enables the language model to retrieve the most up-to-date information directly from the live knowledge base at query time without retraining. Fine-t

0

ASAdi Shikopeningthehood.hashnode.devJul 7 · 8 min read

APIs Were the First Layer. Training Is the Next One

We all see the world changing. A few years ago, AI was not really accessible to most builders. The important research existed long before ChatGPT, including the 2017 paper Attention Is All You Need, w

0

NSNeeloppher Syedneeloppher.hashnode.devMay 30 · 5 min read

Fine-Tuning Qwen2.5-0.5B to Write SRE Post-Mortem Summaries

Writing post-mortem root-cause summaries is time-consuming and inconsistent. Junior SREs miss contributing factors. Senior SREs write summaries that vary in depth and structure. Zero-shot LLMs produce

0

HAHarsh Agaleharshagale.hashnode.devMay 22 · 5 min read

How I Fine-Tuned Llama 2 Using QLoRA on Free GPU Resources

Training and fine-tuning Large Language Models (LLMs) is often considered expensive and hardware-intensive. Most tutorials online assume access to powerful GPUs with large amounts of VRAM, which can b

0

#finetuning

Search Hashnode

#finetuning

Explore Hashnode

Trending tags this week

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

How to Customize an LLM for AI Agents using SFT and QLoRA

Comparing Fine-Tuning Strategies: Which Parts of a GPT Model Should We Update?

RAG or Fine-Tuning? An AI Development Services Comparison

APIs Were the First Layer. Training Is the Next One

Fine-Tuning Qwen2.5-0.5B to Write SRE Post-Mortem Summaries

How I Fine-Tuned Llama 2 Using QLoRA on Free GPU Resources