kyegomez/TinyGPTV

Simple Implementation of TinyGPTV in super simple Zeta lego blocks

22
/ 100
Experimental

This project helps machine learning engineers or researchers working with large language models to build and experiment with specific architectural components. It provides pre-built, simple implementations of key elements like multi-head attention, LoRA, and various normalization layers, allowing for rapid prototyping of new model designs. You would use this if you're developing custom large language models or exploring novel neural network architectures, taking raw input data (tensors) and producing processed tensors for further model layers.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher designing or experimenting with new large language model architectures and need modular building blocks.

Not ideal if you are looking for a pre-trained, ready-to-use large language model for direct application rather than for architectural development.

large-language-model-development neural-network-architecture model-prototyping deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Nov 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/TinyGPTV"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.