BobMcDear/trap
Autoregressive transformers in APL
This project offers a complete, self-contained implementation of autoregressive transformers (like GPT2) written in APL. It allows you to feed in text or other sequential data and train a model from scratch, then generate new text sequences. It's designed for deep learning researchers or APL enthusiasts who want to understand and modify the core algorithms of large language models without relying on complex, specialized frameworks.
107 stars. No commits in the last 6 months.
Use this if you are an APL programmer or researcher wanting to deeply understand, experiment with, and potentially modify the inner workings of an autoregressive transformer model at a fundamental level.
Not ideal if you need a high-performance deep learning solution for production use or are not proficient in APL, as it is currently significantly slower than frameworks like PyTorch and requires APL knowledge to use effectively.
Stars
107
Forks
6
Language
APL
License
MIT
Category
Last pushed
Sep 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/BobMcDear/trap"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LowinLi/transformers-stream-generator
This is a text generation method which returns a generator, streaming out each token in...
ystemsrx/mini-nanoGPT
One-click training of your own GPT. Training a GPT has never been easier for beginners. /...
jaymody/picoGPT
An unnecessarily tiny implementation of GPT-2 in NumPy.
kyegomez/AttentionGrid
A network of attention mechanisms at your fingertips. Unleash the potential of attention...
kamalkraj/minGPT-TF
A minimal TF2 re-implementation of the OpenAI GPT training