m-a-n-i-f-e-s-t/retention
Language modeling with linear-cost context
This project offers a specialized PyTorch layer that helps researchers and developers build large language models more efficiently. It processes long sequences of text data, like code or extensive documents, and outputs an optimized representation that requires less computational power. This is ideal for those working on advanced AI applications who need to manage very long text contexts without prohibitive costs.
117 stars. No commits in the last 6 months.
Use this if you are developing large language models and need to process extremely long text sequences efficiently for both training and real-time text generation.
Not ideal if you are working with short text snippets, don't have access to CUDA-enabled GPUs, or are not building custom deep learning models.
Stars
117
Forks
14
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Sep 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/m-a-n-i-f-e-s-t/retention"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kermitt2/delft
a Deep Learning Framework for Text https://delft.readthedocs.io/
yoeo/guesslang
Detect the programming language of a source code
matthewdeanmartin/whats_that_code
detect programming language of source in pure python from an ensemble of classifiers
airalcorn2/Deep-Semantic-Similarity-Model
My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent...
christiansafka/img2vec
:fire: Use pre-trained models in PyTorch to extract vector embeddings for any image