The Kaitchup – AI on a Budget

The Kaitchup – AI on a Budget

Share this post

The Kaitchup – AI on a Budget
The Kaitchup – AI on a Budget
SmolLM: Full Fine-tuning and Aligning Tiny LLMs on Your Computer
Copy link
Facebook
Email
Notes
More

SmolLM: Full Fine-tuning and Aligning Tiny LLMs on Your Computer

With supervised fine-tuning and distilled DPO

Benjamin Marie's avatar
Benjamin Marie
Aug 08, 2024
∙ Paid
11

Share this post

The Kaitchup – AI on a Budget
The Kaitchup – AI on a Budget
SmolLM: Full Fine-tuning and Aligning Tiny LLMs on Your Computer
Copy link
Facebook
Email
Notes
More
9
Share
Generated with DALL-E

Recent large language models (LLMs) have billions of parameters. They are usually too large to run on low-cost hardware or small devices efficiently. Among the small LLMs, we currently have good models, such as Phi-3 mini (3.8B parameters), which perform well for language generation tasks but are still too large for many use cases.

Phi-3 mini: Fine-tuning and Quantization on Your Computer

Phi-3 mini: Fine-tuning and Quantization on Your Computer

Benjamin Marie
·
May 2, 2024
Read full story

Apple OpenELM LLMs are smaller alternatives. The smallest OpenELM has 270M parameters and can be quickly fine-tuned on-device. However, the model struggles to follow instructions, even after fine-tuning.

Fine-tune Tiny Chat Models with Apple OpenELM and ORPO

Fine-tune Tiny Chat Models with Apple OpenELM and ORPO

Benjamin Marie
·
May 9, 2024
Read full story

Hugging Face launched even smaller LLMs: SmolLM, 135M, 360M, and 1.7B parameter LLMs.

The Kaitchup – AI on a Budget is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.

In this article, I review SmolLM. We will see how Hugging Face made them. I show how to fine-tune SmolLM for chat applications, focusing on the 135M and 360M versions, and align the models with human preferences using the DPO technique. The main purpose of this article is to show how to fully fine-tune and align tiny LLMs on consumer hardware. If you have high-quality training data for a specific domain that doesn't require complex reasoning, you can successfully fine-tune SmolLM within a few hours on your computer.

My notebook for fine-tuning and aligning tiny LLMs on consumer GPUs is available here:

Get the notebook (#93)

*Last update: May 26, 2025*

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 The Kaitchup
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More