The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning. Learn more →
Top 23 Python attention Projects
-
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
LongNet
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
-
punctuator2
A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
-
open-musiclm
Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.
-
PEN-Net-for-Inpainting
[CVPR'2019] PEN-Net: Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting
-
DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in "Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation"
-
gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
-
ScreenAI
Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"
-
GanVinci
Photorealistic human image editing with GANs - Reimplementation of the paper "FEAT: Face Editing with Attention" with additional changes and improvements.
-
multiscale-adversarial-attention-gates
Code for the paper: Valvano G. et al. (2021), Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates
-
vision_transformers
Vision Transformers for image classification, image segmentation, and object detection.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
Project mention: ElevenLabs Launches Voice Translation Tool to Break Down Language Barriers | news.ycombinator.com | 2023-10-10The transformer model was invented to attend to context over the entire sequence length. Look at how the original authors used the Transformer for NMT in the original Vaswani et al publication. https://github.com/jadore801120/attention-is-all-you-need-py...
Project mention: The Secret Sauce behind 100K context window in LLMs: all tricks in one place | news.ycombinator.com | 2023-06-17https://github.com/google-research/long-range-arena
If you want to talk immature looking, longnet wouldn't even compile. That's a big oof, considering it's a python and usually nonworking code is good enough to generate byte code. (also it has hard-coded dtype and device)
I'm working on a personal project where I'm planning to create a fine-tuned version of Music LM, but I'm not sure if there are any pretrained weights that I can use that are available to the public. The closest thing that I can find is this: GitHub - zhvng/open-musiclm: Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.which is a modified, custom version of MusicLM, but I'm looking for something closer to the paper. Does anyone have any resources on this?
Project mention: Implementation of Google's ScreenAI: Vision-Lang Model for UI and Understanding | news.ycombinator.com | 2024-04-09
Project mention: Artificial intelligence can revolutionise science | news.ycombinator.com | 2023-09-15I don't know. As for "literature-based discovery," this project/paper sounded like a pretty big deal when it came out a few years ago: https://github.com/materialsintelligence/mat2vec . And I see this thing came out more recently: https://github.com/anthony-wang/CrabNet .
Of course not all fields lend themselves as well to this as does materials science.
Pose transfer should be relatively easy task nowadays but I can't find working code apart from https://github.com/prasunroy/pose-transfer which doesn't give good result (the output's face always look like a fashion model).
Python attention related posts
- ElevenLabs Launches Voice Translation Tool to Break Down Language Barriers
- LongLlama
- LongNet: Scaling Transformers to 1,000,000,000 Tokens
- Which features you wish that were added to Character Ai?
- Why AI will not replace programmers.
- An open model that beats ChatGPT. We're seeing a real shift towards open source models that will accelerate in the coming weeks.
- GitHub - kyegomez/LongNet: Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
-
A note from our sponsor - WorkOS
workos.com | 25 Apr 2024
Index
What are some of the best open-source attention projects in Python? This list will help you:
Project | Stars | |
---|---|---|
1 | attention-is-all-you-need-pytorch | 8,432 |
2 | scenic | 2,995 |
3 | transformer-pytorch | 2,152 |
4 | ABSA-PyTorch | 1,945 |
5 | gansformer | 1,302 |
6 | performer-pytorch | 1,029 |
7 | graphtransformer | 804 |
8 | long-range-arena | 682 |
9 | LongNet | 650 |
10 | punctuator2 | 648 |
11 | open-musiclm | 477 |
12 | PEN-Net-for-Inpainting | 343 |
13 | how_attentive_are_gats | 275 |
14 | DeepViewAgg | 215 |
15 | gnn-lspe | 214 |
16 | ScreenAI | 174 |
17 | Perceiver | 85 |
18 | CrabNet | 81 |
19 | pose-transfer | 55 |
20 | LFattNet | 53 |
21 | GanVinci | 50 |
22 | multiscale-adversarial-attention-gates | 41 |
23 | vision_transformers | 28 |
Sponsored