Training & Fine-Tuning

How to train your own model? Here is everything you need to know!

Learnings

📄️ Avoiding memory-leaks when training on MPS

Call the following function after each training step:

📄️ Choosing the right model

The main constraints when picking a model for a given task are:

📄️ Create your own datasets for fine-tuning

When fine-tuning, you need to provide data to your model.

📄️ Debugging Machine Learning Models

📄️ Fine-tuning all the weights of a model

Is it possible to fine-tune all the weights of a model when training ?

📄️ How do you fine-tune a model using peft

Let's say you have a model variable containing your model as seen in

📄️ How do you produce text from a text generation model

We use the pytorch and transformers (from huggingface) libraries to run our

📄️ How to repurpose networks without fine-tuning

Let's say you can a neural network that generates code, but you want to use it

📄️ Loading a model from hugging face

Hugging face is a hub that stores machine learning models, datasets and a lot of

📄️ Machine learning is different from programming

As a developper doing a new program, you mostly knows the inputs you will

📄️ Mixture of art and science

Working with people in machine learning was surprising at first.

📄️ Optimiser

As explained in Train a neural network,

📄️ Preparing a model for PEFT

Let's start by importing the relevant peft function we'll need.

📄️ Saving PEFT models

Once your model is trained you need to save it to not lose the hours of

📄️ Training a model

Once your model is ready and you have your data, you are ready to start training

📄️ Using QLora to fine-tune a model

https://github.com/artidoro/qlora