Show HN: Deep learning framework from scratch, trains GPT-2 in 3 days (github.com)

I wanted to share Tricycle (https://github.com/bclarkson-code/Tricycle), a deep learning framework I built completely from scratch from Autograd to a GPT.

I wanted a library that is fast and feature rich enough to train actual models while being simple enough that anyone with a bit of python experience can understand what is going on.

The biggest milestone so far is training GPT-2 (124M) on 2.3B tokens in just under 3 days on my GPU (RTX 3090).

So far, I've added the following to Tricycle:

- An automatic differentiation engine

- General matrix operations with einsum

- Standard network layers (Dense, ReLU, GeLU etc)

- Transformer blocks (MultiHeadSelfAttention and MLP blocks)

- Optimisers (SGD, AdamW)

- GPT-2

- etc

The project is still under active development, I'm in the process of adding mixed precision and multi-gpu support with the goal of scaling up to larger models.

To see it in action, the best place to start is train_smol_gpt.py which will train GPT-2 from scratch.

Let me know what you think!