bhavnicksm/vanilla-transformer-jax
JAX/Flax implimentation of 'Attention Is All You Need' by Vaswani et al. (https://arxiv.org/abs/1706.03762)
This is a foundational building block for artificial intelligence developers working on advanced natural language processing. It takes raw text or sequences, processes them using a specific neural network architecture, and outputs numerical representations that can be used for tasks like translation, summarization, or text generation. It's intended for AI researchers and machine learning engineers building and experimenting with cutting-edge models.
No commits in the last 6 months. Available on PyPI.
Use this if you are an AI developer who needs a robust, ready-to-use implementation of the original Transformer architecture in JAX/Flax for research or building new NLP applications.
Not ideal if you are looking for a pre-trained model for immediate use or if you are not comfortable working with machine learning frameworks like JAX/Flax.
Stars
15
Forks
3
Language
Python
License
MIT
Category
Last pushed
Aug 16, 2021
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/bhavnicksm/vanilla-transformer-jax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
jadore801120/attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
kyegomez/SparseAttention
Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with...
AbdelStark/attnres
Rust implementation of Attention Residuals from MoonshotAI/Kimi
sunnynguyen-ai/llm-attention-visualizer
Interactive tool for analyzing attention patterns in transformer models with layer-wise...