Tag feed

#lora

71 posts3 followers

Explore Hashnode

Alternatives

Trending tags this week

AAAbstract Algorithmsabstractalgorithms.devApr 18 · 30 min read

Fine-Tuning LLMs: The Complete Engineer's Guide to SFT, LoRA, and RLHF

TLDR: A pretrained LLM is a generalist. Fine-tuning makes it a specialist. Supervised Fine-Tuning (SFT) teaches it your domain's language through labeled examples. LoRA does the same with 99% fewer tr

0

JKJangwook Kimeffloow.hashnode.devApr 17 · 12 min read

Fine-Tune LLMs with LoRA and QLoRA: 2026 Guide

Two years ago, fine-tuning a large language model required a rack of A100s, a machine learning team, and a five-figure cloud bill. In 2026, a single RTX 4070 Ti is enough to specialize a 7B model on your domain data — in an afternoon. That shift happ...

1

E

Iiniyarajaniniyarajanhashnodedev.hashnode.devApr 13 · 8 min read

LoRA Adapters On-Device iOS: Apple's Game-Changing AI Future

Picture this: You're debugging an iOS app at 2 AM, desperately searching Stack Overflow for that one specific CoreML error. But instead of leaving your app, you ask your on-device AI assistant—trained specifically on your codebase using LoRA adapters...

0

RSRahul Sehrawatai-zero-to-hero.hashnode.devApr 13 · 11 min read

Fine-Tuning in 2026: What It Is Still Good For

Every team I've worked with has asked this question at some point: "Should we fine-tune our own model?" The question almost always comes wrapped in optimism — a PM or engineer has read an article about fine-tuning, talked to a vendor, seen a benchmar...

0

AAmegillasparktastic.hashnode.devApr 5 · 13 min read

Training a LoRA with Unsloth on DGX Spark

Having done a long detour through manually reviewing and finessing my training data, this weekend I was finally ready to train the LoRAs for my poster generation project. I have two planned: One to g

0

JWJames Wucalm-engineering-loud-bugs.hashnode.devMar 24 · 10 min read

Types of Fine-Tuning Approaches: A No-Fluff Guide for AI Practitioners

Not all fine-tuning is the same. The method you pick determines your compute bill, your results, and whether your model forgets everything it already knew. Fine-tuning is not a single button you press

0

AAAbstract Algorithmsabstractalgorithms.devMar 9 · 14 min read

PEFT, LoRA, and QLoRA: A Practical Guide to Efficient LLM Fine-Tuning

TLDR: Full fine-tuning updates every model weight, which is expensive in memory, compute, and storage. PEFT methods update only a small trainable slice. LoRA learns low-rank adapters on top of frozen

0

AAAbstract Algorithmsabstractalgorithms.devMar 9 · 13 min read

LoRA Explained: How to Fine-Tune LLMs on a Budget

TLDR: Fine-tuning a 7B-parameter LLM updates billions of weights and requires expensive GPUs. LoRA (Low-Rank Adaptation) freezes the original weights and trains only tiny adapter matrices that are add

0

AAiksktiioi.hashnode.devMar 2 · 15 min read

Choosing a LoRa Module from a Power Consumption Perspective

What you will get from this article 1. You will stop judging power consumption with only one current number. 2. You will use a simple “power budget” method to estimate how many days your project can r

0

RARana Adeel Tahirthelatentlament.hashnode.devFeb 10 · 3 min read

Fine-Tuning BLIP-2 with LoRA

In my journey to dive deeper into multimodal AI systems, I decided to fine-tune BLIP-2, a powerful vision-language model trained on the Flickr8k dataset to generate image captions. What made this more exciting was integrating LoRA (Low-Rank Adaptatio...

0

#lora

Search Hashnode

#lora

Explore Hashnode

Trending tags this week

Fine-Tuning LLMs: The Complete Engineer's Guide to SFT, LoRA, and RLHF

Fine-Tune LLMs with LoRA and QLoRA: 2026 Guide

LoRA Adapters On-Device iOS: Apple's Game-Changing AI Future

Fine-Tuning in 2026: What It Is Still Good For

Training a LoRA with Unsloth on DGX Spark

Types of Fine-Tuning Approaches: A No-Fluff Guide for AI Practitioners

PEFT, LoRA, and QLoRA: A Practical Guide to Efficient LLM Fine-Tuning

LoRA Explained: How to Fine-Tune LLMs on a Budget

Choosing a LoRa Module from a Power Consumption Perspective

Fine-Tuning BLIP-2 with LoRA