---
title: "#fine-tuning articles | Hashnode"
description: "Explore 40 articles tagged #fine-tuning on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/fine-tuning"
---

Tag

# #fine-tuning

40 posts · 1 followers

[Michał Piszczek](https://hashnode.com/@michalpiszczek) · [Nov 9](https://hashnode.com/posts/mode-collapse-is-a-default-not-a-law-what-preference-tuning-does-to-variety/6af2507576ce69d8c82799e1)

### [Mode collapse is a default, not a law: what preference tuning does to variety](https://piszczek.hashnode.dev/mode-collapse-is-a-default-not-a-law-what-preference-tuning-does-to-variety?utm_source=hashnode&utm_medium=feed)

Why 25 models give you two metaphors, and why temperature doesn't fix it

11 min read · [piszczek.hashnode.dev](https://piszczek.hashnode.dev/mode-collapse-is-a-default-not-a-law-what-preference-tuning-does-to-variety?utm_source=hashnode&utm_medium=feed)

[TechTIQ Inc](https://hashnode.com/@techtiqinc) · [Oct 30](https://hashnode.com/posts/rag-vs-fine-tuning-vs-prompt-engineering-choosing-the-right-approach/6ae4169919da51502f60cc17)

### [RAG vs Fine-Tuning vs Prompt Engineering: Choosing the Right Approach](https://techtiqinc.hashnode.dev/rag-vs-fine-tuning-vs-prompt-engineering-choosing-the-right-approach?utm_source=hashnode&utm_medium=feed)

A practical guide to choosing between prompt engineering, RAG, and fine-tuning for your LLM project.

4 min read · [techtiqinc.hashnode.dev](https://techtiqinc.hashnode.dev/rag-vs-fine-tuning-vs-prompt-engineering-choosing-the-right-approach?utm_source=hashnode&utm_medium=feed)

[Rebiha.com](https://hashnode.com/@rebiha) · [Oct 20](https://hashnode.com/posts/llm-fine-tuning-services-how-to-choose-the-right-provider-in-2026/6ad7a0cdce9be325f0b93e5e)

### [LLM Fine-Tuning Services: How to Choose the Right Provider in 2026](https://rebiha.hashnode.dev/llm-fine-tuning-services-how-to-choose-the-right-provider-in-2026?utm_source=hashnode&utm_medium=feed)

A practical framework for evaluating model support, training data, QLoRA, privacy, evaluation, and model ownership.

6 min read · [rebiha.hashnode.dev](https://rebiha.hashnode.dev/llm-fine-tuning-services-how-to-choose-the-right-provider-in-2026?utm_source=hashnode&utm_medium=feed)

[Taha hussein](https://hashnode.com/@tahahussein) · [Oct 20](https://hashnode.com/posts/fine-tuning-vs-lora-vs-qlora-understanding-efficient-llm-adaptation/6ad7308e25f7cd8d95e2b142)

### [Fine-Tuning vs LoRA vs QLoRA: Understanding Efficient LLM Adaptation](https://tahahussein.hashnode.dev/fine-tuning-vs-lora-vs-qlora-understanding-efficient-llm-adaptation?utm_source=hashnode&utm_medium=feed)

Learn 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](https://tahahussein.hashnode.dev/fine-tuning-vs-lora-vs-qlora-understanding-efficient-llm-adaptation?utm_source=hashnode&utm_medium=feed)

[Viraj Sawant](https://hashnode.com/@viraaj) · [Oct 15](https://hashnode.com/posts/directional-ablation-can-t-see-24-rotation-of-the-refusal-direction/6ad0ab8ff68738517b9e43ae)

### [Directional Ablation Can't see 24° Rotation of the Refusal Direction](https://mechanistic-artifacts.hashnode.dev/directional-ablation-can-t-see-24-rotation-of-the-refusal-direction?utm_source=hashnode&utm_medium=feed)

Why directional ablation fails to detect refusal vector rotation after fine-tuning, and how calibration decouples estimate drift from safety.

23 min read · [mechanistic-artifacts.hashnode.dev](https://mechanistic-artifacts.hashnode.dev/directional-ablation-can-t-see-24-rotation-of-the-refusal-direction?utm_source=hashnode&utm_medium=feed)

[Aleksei Romanov](https://hashnode.com/@gfactor) · [Sep 26](https://hashnode.com/posts/lora-dora-the-math-memory-and-trade-offs/6ab7ee6c0c027d01840127f8)

### [LoRA & DoRA: The Math, Memory, and Trade-offs](https://gfactor.hashnode.dev/lora-dora-the-math-memory-and-trade-offs?utm_source=hashnode&utm_medium=feed)

LoRA and DoRA explained: matrix shapes, the geometry of weight decomposition, exact memory math for a 27B model, and what the DoRA benchmarks support.

10 min read · [gfactor.hashnode.dev](https://gfactor.hashnode.dev/lora-dora-the-math-memory-and-trade-offs?utm_source=hashnode&utm_medium=feed)

[Fotie M. Constant](https://hashnode.com/@fotiecodes) · [Sep 23](https://hashnode.com/posts/project-turaco-is-finally-showing-promise/6ab3cb6a344682413e550c4d)

### [Project Turaco Is Finally Showing Promise](https://blog.fotiecodes.com/project-turaco-is-finally-showing-promise?utm_source=hashnode&utm_medium=feed)

For more than a year, I have been trying to answer one question: can we build a machine translation model that translates English into natural Cameroon Pidgin without sounding like it is guessing? Tha

3 min read · [blog.fotiecodes.com](https://blog.fotiecodes.com/project-turaco-is-finally-showing-promise?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/project-turaco-is-finally-showing-promise/6ab3cb6a344682413e550c4d)

[Taha hussein](https://hashnode.com/@tahahussein) · [Sep 18](https://hashnode.com/posts/fine-tuning-an-llm-what-actually-happens-under-the-hood/6aacfeb891ce0511ce99e211)

### [Fine-Tuning an LLM: What Actually Happens Under the Hood?](https://tahahussein.hashnode.dev/fine-tuning-an-llm-what-actually-happens-under-the-hood?utm_source=hashnode&utm_medium=feed)

Learn how LLM fine-tuning works under the hood, including training, parameters, LoRA, PEFT, and the differences between fine-tuning, RAG

7 min read · [tahahussein.hashnode.dev](https://tahahussein.hashnode.dev/fine-tuning-an-llm-what-actually-happens-under-the-hood?utm_source=hashnode&utm_medium=feed)

[Rahul Sai Indeevar V](https://hashnode.com/@rahul-ai) · [Sep 16](https://hashnode.com/posts/parameter-efficient-fine-tuning-from-lora-to-qlora/6aaa2c781ddc873f8d269492)

### [Parameter-Efficient Fine-Tuning: From LoRA to QLoRA](https://rahul-ai.hashnode.dev/parameter-efficient-fine-tuning-from-lora-to-qlora?utm_source=hashnode&utm_medium=feed)

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

10 min read · [rahul-ai.hashnode.dev](https://rahul-ai.hashnode.dev/parameter-efficient-fine-tuning-from-lora-to-qlora?utm_source=hashnode&utm_medium=feed)

[Rahul Sai Indeevar V](https://hashnode.com/@rahul-ai) · [Sep 8](https://hashnode.com/posts/llm-post-training-from-full-fine-tuning-to-peft-adapters-and-soft-prompts/6a9fd28f6e353022f86c7d9d)

### [LLM Post-Training: From Full Fine-Tuning to PEFT, Adapters, and Soft Prompts](https://rahul-ai.hashnode.dev/llm-post-training-from-full-fine-tuning-to-peft-adapters-and-soft-prompts?utm_source=hashnode&utm_medium=feed)

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

14 min read · [rahul-ai.hashnode.dev](https://rahul-ai.hashnode.dev/llm-post-training-from-full-fine-tuning-to-peft-adapters-and-soft-prompts?utm_source=hashnode&utm_medium=feed)
