Maxime Labonne – Medium

Maxime Labonne

Featured Book

Hands-On Graph Neural Networks Using Python

Hands-On Graph Neural Networks Using Python

Design robust graph neural networks with PyTorch Geometric by combining graph theory and neural networks with the latest developments and apps.

2023

Stories

Maxime Labonne
in
Towards Data Science

Fine-tune Llama 3 with ORPO

A cheaper and faster unified fine-tuning technique

8 min readApr 19, 2024

--

8

Fine-tune Llama 3 with ORPO

--

8

Maxime Labonne
in
Towards Data Science

Create Mixtures of Experts with MergeKit

Combine multiple models into a single MoE

9 min readMar 27, 2024

--

8

Create Mixtures of Experts with MergeKit

--

8

Maxime Labonne
in
Towards Data Science

Merge Large Language Models with mergekit

Create your own models easily, no GPU required!

11 min readJan 8, 2024

--

17

Merge Large Language Models with mergekit

--

17

Maxime Labonne
in
Towards Data Science

Fine-tune a Mistral-7b model with Direct Preference Optimization

Boost the performance of your supervised fine-tuned models

10 min readJan 1, 2024

--

10

Fine-tune a Mistral-7b model with Direct Preference Optimization

--

10

Maxime Labonne
in
Towards Data Science

ExLlamaV2: The Fastest Library to Run LLMs

Quantize and run EXL2 models

6 min readNov 20, 2023

--

6

ExLlamaV2: The Fastest Library to Run LLMs

--

6

Maxime Labonne
in
Towards Data Science

Quantize Llama models with GGUF and llama.cpp

GGML vs. GPTQ vs. NF4

9 min readSep 4, 2023

--

5

Quantize Llama models with GGUF and llama.cpp

--

5

Maxime Labonne
in
Towards Data Science

A Beginner’s Guide to LLM Fine-Tuning

How to fine-tune Llama and other LLMs with one tool

8 min readAug 30, 2023

--

7

A Beginner’s Guide to LLM Fine-Tuning

--

7

Maxime Labonne
in
Towards Data Science

Graph Convolutional Networks: Introduction to GNNs

A step-by-step guide using PyTorch Geometric

16 min readAug 14, 2023

--

7

Graph Convolutional Networks: Introduction to GNNs

--

7

Maxime Labonne
in
Towards Data Science

4-bit Quantization with GPTQ

Quantize your own LLMs using AutoGPTQ

10 min readJul 31, 2023

--

3

4-bit Quantization with GPTQ

--

3

Maxime Labonne
in
Towards Data Science

Fine-Tune Your Own Llama 2 Model in a Colab Notebook

A practical introduction to LLM fine-tuning

12 min readJul 25, 2023

--

43

Fine-Tune Your Own Llama 2 Model in a Colab Notebook

--

43

Maxime Labonne

Maxime Labonne

Book Author

Ph.D., Staff ML Scientist @ Liquid AI • Author of "Hands-On Graph Neural Networks" • x.com/maximelabonne

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams