transformers • Rank 38.7 • Science 64%

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

openprompt • Rank 18.3 • Science 72%

An Open-Source Framework for Prompt-Learning.

torchao • Rank 25.9 • Science 64%

PyTorch native quantization and sparsity for training and inference

onnx2tf • Rank 22.1 • Science 67%

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.

lm-eval • Rank 28.4 • Science 59%

A framework for few-shot evaluation of language models.

smart-transformers • Rank 7.9 • Science 77%

Smart Transformers are a versatile machine learning tool that can be integrated with Pytorch, TensorFlow, and JAX. Smart transformers provide accurate computations required for cryptographic algorithms. These transformers is that they are independent modules, making it efficient to experiment with various research projects related to cryptanalysis

uform • Rank 15.6 • Science 64%

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

mmsegmentation • Rank 25.5 • Science 54%

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

en-transformer • Rank 11.6 • Science 67%

Implementation of E(n)-Transformer, which incorporates attention mechanisms into Welling's E(n)-Equivariant Graph Neural Network

rwkv-lm • Rank 11.2 • Science 67%

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

avi-mmdet • Rank 29.1 • Science 46%

OpenMMLab Detection Toolbox and Benchmark

autono • Rank 7.2 • Science 67%

A ReAct-Based Highly Robust Autonomous Agent Framework.

torchdistill • Rank 15.0 • Science 59%

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

https://github.com/torchmd/torchmd-net • Rank 14.5 • Science 59%

Training neural network potentials

https://github.com/nixtla/neuralforecast • Rank 23.6 • Science 46%

Scalable and user friendly neural :brain: forecasting algorithms.

llms-from-scratch • Rank 14.9 • Science 54%

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

https://github.com/timeseriesai/tsai • Rank 21.4 • Science 46%

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

https://github.com/google/trax • Rank 20.8 • Science 46%

Trax — Deep Learning with Clear Code and Speed

multilspy • Rank 18.6 • Science 46%

multilspy is a lsp client library in Python intended to be used to build applications around language servers.

transformer-srl • Rank 10.4 • Science 54%

Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.

ultralyticspro • Rank 9.7 • Science 54%

🔥🔥🔥 专注于YOLO11，YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

question_generation • Rank 8.7 • Science 54%

Neural question generation using transformers

monitors4codegen • Rank 7.0 • Science 54%

Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.

sorsa • Rank 6.2 • Science 54%

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

caspr • Rank 5.5 • Science 54%

CASPR is a deep learning framework applying transformer architecture to learn and predict from tabular data at scale.

text-case • Rank 14.9 • Science 44%

Convert text between `camelCase`, `PascalCase`, `Capital Case`, `Header-Case`, `Title Case`, `path/case`, `snake_case`, `param-case`, `dot.case`, `CONSTANT_CASE`, `lower case`, `lOWER CASE FIRST`, `UPPER CASE`, `Upper case first` and other

proteinn-structure-predictor • Rank 1.6 • Science 57%

A transformer network trained to predict end-to-end single sequence protein structure as a set of angles given amino acid sequences.

image-captioning-mobilenet-llama3 • Rank 1.8 • Science 54%

Image Captioning With MobileNet-LLaMA 3

transformers • Rank 1.6 • Science 54%

Flexible transformer implementation for research

stormtrooper • Rank 7.6 • Science 44%

Zero/few shot learning components for scikit-learn pipelines with LLMs and transformers.

https://github.com/csinva/interpretable-embeddings • Rank 4.7 • Science 46%

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

https://github.com/awslabs/sockeye • Rank 17.7 • Science 33%

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

sparql-transformer • Rank 10.0 • Science 39%

A more handy way to use SPARQL data in your web app

https://github.com/google-research/jestimator • Rank 10.8 • Science 36%

Amos optimizer with JEstimator lib.

gpt • Rank 1.8 • Science 44%

Generative Pre-trained Transformer in PyTorch from scratch

computer-vision-in-action • Rank 9.3 • Science 36%

A computer vision closed-loop learning platform where code can be run interactively online. 学习闭环《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（持续更新中 ...） 📘 在线电子书 https://charmve.github.io/computer-vision-in-action/ 👇项目主页

https://github.com/cedrickchee/awesome-transformer-nlp • Rank 9.3 • Science 36%

A curated list of NLP resources focused on Transformer networks, attention mechanism, GPT, BERT, ChatGPT, LLMs, and transfer learning.

gcvit • Rank 9.0 • Science 36%

Tensorflow 2.0 Implementation of GCViT: Global Context Vision Transformer

https://github.com/hongbo-miao/hongbomiao.com • Rank 17.3 • Science 26%

A personal research and development (R&D) lab that facilitates the sharing of knowledge.

https://github.com/bigscience-workshop/petals • Rank 18.7 • Science 23%

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

https://github.com/bowang-lab/ecg-fm • Rank 5.0 • Science 36%

An electrocardiogram analysis foundation model.

https://github.com/longxingtan/time-series-prediction • Rank 14.4 • Science 26%

tfts: Time Series Deep Learning Models in TensorFlow

https://github.com/astrazeneca/selfpad • Rank 2.5 • Science 36%

The official implementation of "Improving Antibody Humanness Prediction using Patent Data".

relora • Rank 6.1 • Science 26%

Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates

https://github.com/ai-forever/mgpt • Rank 7.0 • Science 23%

Multilingual Generative Pretrained Model

https://github.com/heidelbergcement/hcrystalball • Rank 16.5 • Science 13%

A library that unifies the API for most commonly used libraries and modeling techniques for time-series forecasting in the Python ecosystem.

conformer • Rank 6.1 • Science 23%

Implementation of the convolutional module from the Conformer paper, for use in Transformers

https://github.com/bytedance/lightseq • Rank 18.7 • Science 10%

LightSeq: A High Performance Library for Sequence Processing and Generation

https://github.com/csinva/gpt-paper-title-generator • Rank 5.7 • Science 20%

Generating paper titles (and more!) with GPT trained on data scraped from arXiv.

band • Rank 8.7 • Science 13%

BAND：BERT Application aNd Deployment, A simple and efficient BERT model training and deployment framework.

https://github.com/bytedance/bytetransformer • Rank 6.9 • Science 13%

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

text-sim • Rank 7.9 • Science 10%

文本相似度（匹配）计算，提供Baseline、训练、推理、指标分析...代码包含TensorFlow/Pytorch双版本

https://github.com/baldassarrefe/performer-gat-shapenet • Rank 0.7 • Science 13%

Performer vs. Graph Attention Network on ShapeNet with GradCAM explanations.

https://github.com/cosbidev/matnet • Rank 2.2 • Science 10%

Multi-Level Fusion and Self-Attention Transformer-Based Model for Multivariate Multi-Step Day-Ahead PV Generation Forecasting

decompose • Science 67%

Principal Component Analysis (PCA) Algorithm was implemented to determine the Functional Age of the Power Transformer using Return Voltage Measurement (RVM). [submitted]

https://github.com/buaadreamer/nlpkiller • Science 13%

nlp intro project

language-pretraining • Science 67%

Pre-training Language Models for Japanese

arrakis-mi • Science 44%

Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.

git • Science 54%

[ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"

grte • Science 65%

Graph Receptive Transformer Encoder

intr • Science 75%

This is an official implementation for [ICLR'24] INTR: Interpretable Transformer for Fine-grained Image Classification.

ecg_classification • Science 49%

Official and maintained implementation of the paper "Exploring Novel Algorithms for Atrial Fibrillation Detection by Driving Graduate Level Education in Medical Machine Learning" (ECG-DualNet) [Physiological Measurement 2022, EMBC 2023].

helical • Science 57%

A framework for state-of-the-art pre-trained bio foundation models on genomics and transcriptomics modalities.

memoria-pytorch • Science 41%

Memoria is a human-inspired memory architecture for neural networks.

https://github.com/amazon-science/gluonmm • Science 36%

A library of transformer models for computer vision and multi-modality research

https://github.com/amazon-science/tubelet-transformer • Science 26%

This is an official implementation of TubeR: Tubelet Transformer for Video Action Detection

hardvs • Science 54%

[AAAI-2024] HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

plankassembly • Science 54%

[ICCV 2023] PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs

bitcoin-trader-ml • Science 44%

Automated 24/7 bitcoin trader for Coinbase using Transformer Neural Networks

community-aware-graph-transformer • Science 67%

Community-aware Graph Transformer (CGT) is a novel Graph Transformer model that utilizes community structures to address node degree biases in message-passing mechanism and developed by NS Lab @ CUK based on pure PyTorch backend.

https://github.com/christophreich1996/swin-transformer-v2 • Science 10%

PyTorch reimplementation of the paper "Swin Transformer V2: Scaling Up Capacity and Resolution" [CVPR 2022].

spatialfusion-lm • Science 26%

SpatialFusion-LM is a real-time spatial reasoning framework that combines neural depth, 3D reconstruction, and language-driven scene understanding.

https://github.com/aveek-saha/transformer • Science 23%

A TensorFlow 2.0 Implementation of the Transformer: Attention Is All You Need

https://github.com/bentoml/transformers-nlp-service • Science 13%

Online Inference API for NLP Transformer models - summarization, text classification, sentiment analysis and more

https://github.com/boniolp/msad • Science 36%

[VLDB 2023] Model Selection for Anomaly Detection in Time Series

final-state-transformer • Science 44%

Machine learning development toolkit built upon Transformer encoder network architectures and tailored for the realm of high-energy physics and particle-collision event analysis.

badtransformer • Science 44%

Simplified and easy-to-understand transformer

qaqg • Science 54%

Indonesian Question Answering and Question Generation using Transformers

awesome-attention-heads • Science 67%

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

network-traffic-transformer • Science 67%

Network Traffic Transformer to learn network dynamics from packet traces. Learn fundamental dynamics with pre-training and fine-tune to multiple applications.

https://github.com/cedrickchee/bert-pytorch • Science 10%

Google AI BERT 2018 pytorch implementation

mlsae • Science 41%

Multi-Layer Sparse Autoencoders (ICLR 2025)

comprehensive-transformer-tts • Science 36%

A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS

cv-3315-is-all-you-need • Science 54%

CV′3315 Is All You Need – Semantic Segmentation Course Competition @ The University of Adelaide

open-muse • Science 54%

Open reproduction of MUSE for fast text2image generation.

spn4cir • Science 54%

[ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives

saits • Science 67%

The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516

deno-nodejs-transformer • Science 44%

A Deno module for transform Deno package to NodeJS package. This module is a modified edition of the JSR package `dnt`.

wordart • Science 54%

The official code of CornerTransformer (ECCV 2022, Oral) on top of MMOCR.

https://github.com/dc-research/tempo • Science 36%

The official code for "TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)". TEMPO is one of the very first open source Time Series Foundation Models for forecasting task v1.0 version.

https://github.com/alan-turing-institute/prompto • Science 26%

An open source library for asynchronous querying of LLM endpoints

superpoint_transformer • Science 67%

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"

renderformer • Science 54%

Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

faceformer • Science 54%

[CVPR 2022] Neural Face Identification in a 2D Wireframe Projection of a Manifold Object

https://github.com/arbit3rr/narx-transformer-soh • Science 13%

https://github.com/cosmaadrian/strawberry-problem • Science 36%

Official repository for "The Strawberry Problem 🍓: Emergence of Character-level Understanding in Tokenized Language Models"

intr-paquetlab • Science 49%

Fork of Imageomics/INTR for paquetlab project

bmt • Science 54%

Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

learning_on_cortical_meshes_with_surface_vision_transformers • Science 54%

Code accompanying the master thesis: Learning on Cortical Meshes with Surface Vision Transformers (SiT)

mazegpt • Science 44%

AI model for making mazes that extends OpenAIs GPT2 model