nanowell/Differential-Transformer-PyTorch

PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture incorporates a novel Differential Attention mechanism, Multi-Head structure, RMSNorm, and SwiGLU.

34
/ 100
Emerging

This project offers a PyTorch implementation of the Differential Transformer architecture, designed as a decoder-only model for advanced sequence modeling. It takes sequential data as input and produces new, contextually relevant sequences as output. This tool is intended for researchers and machine learning engineers working on developing or experimenting with large language models.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer interested in exploring a novel transformer architecture for sequence generation tasks.

Not ideal if you are looking for a ready-to-use application or a high-level API for deploying pre-trained LLMs without diving into model architecture.

large-language-models sequence-generation deep-learning-research natural-language-processing neural-network-architecture
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

86

Forks

6

Language

Python

License

MIT

Last pushed

Oct 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/nanowell/Differential-Transformer-PyTorch"

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