transformers
🤗 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.
onnx2tf
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.
smart-transformers
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
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
en-transformer
Implementation of E(n)-Transformer, which incorporates attention mechanisms into Welling's E(n)-Equivariant Graph Neural Network
rwkv-lm
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.
torchdistill
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/nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
llms-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
https://github.com/timeseriesai/tsai
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
multilspy
multilspy is a lsp client library in Python intended to be used to build applications around language servers.
transformer-srl
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.
monitors4codegen
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
SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models
caspr
CASPR is a deep learning framework applying transformer architecture to learn and predict from tabular data at scale.
text-case
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
A transformer network trained to predict end-to-end single sequence protein structure as a set of angles given amino acid sequences.
stormtrooper
Zero/few shot learning components for scikit-learn pipelines with LLMs and transformers.
https://github.com/csinva/interpretable-embeddings
Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)
https://github.com/awslabs/sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
https://github.com/google-research/jestimator
Amos optimizer with JEstimator lib.
computer-vision-in-action
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
A curated list of NLP resources focused on Transformer networks, attention mechanism, GPT, BERT, ChatGPT, LLMs, and transfer learning.
gcvit
Tensorflow 2.0 Implementation of GCViT: Global Context Vision Transformer
https://github.com/hongbo-miao/hongbomiao.com
A personal research and development (R&D) lab that facilitates the sharing of knowledge.
https://github.com/bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
https://github.com/bowang-lab/ecg-fm
An electrocardiogram analysis foundation model.
https://github.com/longxingtan/time-series-prediction
tfts: Time Series Deep Learning Models in TensorFlow
https://github.com/astrazeneca/selfpad
The official implementation of "Improving Antibody Humanness Prediction using Patent Data".
relora
Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
https://github.com/heidelbergcement/hcrystalball
A library that unifies the API for most commonly used libraries and modeling techniques for time-series forecasting in the Python ecosystem.
conformer
Implementation of the convolutional module from the Conformer paper, for use in Transformers
https://github.com/bytedance/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation
https://github.com/csinva/gpt-paper-title-generator
Generating paper titles (and more!) with GPT trained on data scraped from arXiv.
band
BAND：BERT Application aNd Deployment, A simple and efficient BERT model training and deployment framework.
https://github.com/bytedance/bytetransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
https://github.com/baldassarrefe/performer-gat-shapenet
Performer vs. Graph Attention Network on ShapeNet with GradCAM explanations.
https://github.com/cosbidev/matnet
Multi-Level Fusion and Self-Attention Transformer-Based Model for Multivariate Multi-Step Day-Ahead PV Generation Forecasting
bitcoin-trader-ml
Automated 24/7 bitcoin trader for Coinbase using Transformer Neural Networks
modular-diffusion
Python library for designing and training your own Diffusion Models with PyTorch
bundoora
Customized development container environment for consistent and efficient execution of machine learning projects.
master-thesis
One Bit at a Time: Impact of Quantisation on Neural Machine Translation
faceformer
[CVPR 2022] Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
https://github.com/anshitag/memit_csk
Source repository for Editing Common Sense in Transformers (EMNLP 2023)
https://github.com/amazon-science/wqa-multi-sentence-inference
This repository contains code used for our Multi Sentence Inference NAACL'22 paper.
https://github.com/arbit3rr/narx-transformer-soh
https://github.com/christophreich1996/swin-transformer-v2
PyTorch reimplementation of the paper "Swin Transformer V2: Scaling Up Capacity and Resolution" [CVPR 2022].
https://github.com/cosmaadrian/strawberry-problem
Official repository for "The Strawberry Problem 🍓: Emergence of Character-level Understanding in Tokenized Language Models"
devformer
[ICML 2023] Official code for "DevFormer: A Symmetric Transformer for Context-Aware Device Placement"
community-aware-graph-transformer
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.
wordart
The official code of CornerTransformer (ECCV 2022, Oral) on top of MMOCR.
awesome-attention-heads
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
https://github.com/cedrickchee/bert-pytorch
Google AI BERT 2018 pytorch implementation
ai-health-agent
This code represents my work for the dissertation project of my MSc at the University of St Andrews.
decompose
Principal Component Analysis (PCA) Algorithm was implemented to determine the Functional Age of the Power Transformer using Return Voltage Measurement (RVM). [submitted]
git
[ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
dpl
[NeurIPS 2023] Multi-fidelity hyperparameter optimization with deep power laws that achieves state-of-the-art results across diverse benchmarks.
spn4cir
[ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
https://github.com/dc-research/tempo
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.
plankassembly
[ICCV 2023] PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs
https://github.com/924973292/fusionreid
【IEEE TITS2025】Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification
superpoint_transformer
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
Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
network-traffic-transformer
Network Traffic Transformer to learn network dynamics from packet traces. Learn fundamental dynamics with pre-training and fine-tune to multiple applications.
final-state-transformer
Machine learning development toolkit built upon Transformer encoder network architectures and tailored for the realm of high-energy physics and particle-collision event analysis.
bmt
Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
spatialfusion-lm
SpatialFusion-LM is a real-time spatial reasoning framework that combines neural depth, 3D reconstruction, and language-driven scene understanding.
saits
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
master-thesis
📄 My Master's Thesis in Computer Science, written at the Norwegian University of Science and Technology (NTNU)
comprehensive-transformer-tts
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