kyegomez/LongNet
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
This project offers a way for machine learning engineers to work with extremely long text or data sequences. It takes existing Transformer models and allows them to process inputs up to a billion tokens, a significant leap beyond typical limits. This helps researchers and developers who are building large language models or other sequence-based AI systems that need to analyze vast amounts of information.
714 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher developing Transformer-based models and need to process sequences far longer than traditional methods allow, such as an entire book or a vast dataset.
Not ideal if you are not a machine learning practitioner working with deep learning models, or if your tasks only involve short to medium length text sequences.
Stars
714
Forks
61
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 07, 2024
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/LongNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in...
pbloem/former
Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)
NVIDIA/FasterTransformer
Transformer related optimization, including BERT, GPT
kyegomez/SimplifiedTransformers
SimplifiedTransformer simplifies transformer block without affecting training. Skip connections,...
ARM-software/keyword-transformer
Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769