Beomi/BitNet-Transformers

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

34
/ 100
Emerging

This project helps machine learning engineers and researchers explore and implement highly efficient large language models. It provides a way to train and use models with significantly reduced memory footprint by converting standard Llama models to a 'bit' representation. The output is a Llama-architecture language model that uses considerably less GPU memory.

313 stars. No commits in the last 6 months.

Use this if you are developing or deploying large language models and need to drastically reduce the GPU memory consumption for training and inference.

Not ideal if you are a non-technical end-user simply looking to use an off-the-shelf language model.

large-language-models model-optimization deep-learning natural-language-processing gpu-memory-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

313

Forks

34

Language

Python

License

Last pushed

Mar 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Beomi/BitNet-Transformers"

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