Andrei Khobnia

MSformer. A novel molecular representation framework via meta structures

Search-R1. Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

openfold. Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

ir-examples. Examples of problem-solving in Information Retrieval, RAG, and Agentic Systems

beir. A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

retrivex. Explainability toolkit for retrieval models. Explain prediction of vector search models (embeddings similarity models, siamese encoders, bi-encoders, dense retrieval models). Debug your vector search models for RAG or agentic AI system.

minihack. MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

teemi. teemi: A Python package for reproducible and FAIR microbial strain construction. Simulate the entire dbtl-cycle, generate genetic parts, design libraries, and track samples. Open-source Python platform for workflow flexibility and automated tasks, accelerating metabolic engineering. Try teemi with our Google Colab notebooks!

lm-polygraph. Python

nanochat. The best ChatGPT that $100 can buy.

bdm-tool. Simple lightweight dataset versioning utility based purely on the file system and symbolic links.

RFdiffusion. Code for running RFdiffusion

graphframes-rs. GraphFrames but in DataFusion

chispa. PySpark test helper methods with beautiful error messages

incubator-graphar. An open source, standard data file format for graph data storage and retrieval.

graphframes. GraphFrames is a package for Apache Spark which provides DataFrame-based Graphs

CTranslate2. Fast inference engine for Transformer models

LLMs-Planning. An extensible benchmark for evaluating large language models on planning

SKURG. Python

LyCORIS. Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

t-few. Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

langchain. The agent engineering platform.

mlc-llm. Universal LLM Deployment Engine with ML Compilation

medmcqa. A large-scale (194k), Multiple-Choice Question Answering (MCQA) dataset designed to address realworld medical entrance exam questions.

GENRE. Autoregressive Entity Retrieval

ThoughtSource. A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

medical-reasoning. Medical reasoning using large language models

knnlm. Python

quart. An async Python micro framework for building web applications.

alfred. ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

hivemind. Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

pygaggle. a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini

pyserini. Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

composer. Supercharge Your Model Training

ivy. Convert Machine Learning Code Between Frameworks

ir_datasets. Provides a common interface to many IR ranking datasets.

AR2. Python

haystack. Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

awesome-feature-engineering. A curated list of resources dedicated to Feature Engineering Techniques for Machine Learning

awesome-open-mlops. The Fuzzy Labs guide to the universe of open source MLOps

grobid. A machine learning software for extracting information from scholarly documents

AutoDeploy. AutoDeploy is a single configuration deployment library

ludwig. Low-code framework for building custom LLMs, neural networks, and other AI models

RECON. This is the code for the paper 'RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network'.

FlowQA. Implementation of conversational QA model: FlowQA (with slight improvement)

minecraft-dialogue-models. Python

ruletaker. Python

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

nmslib. Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

pet. This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

bort. Repository for the paper "Optimal Subarchitecture Extraction for BERT"

pytorch_geometric. Graph Neural Network Library for PyTorch

ariadne. Jupyter Notebook

serve. ☁️ Build multimodal AI applications with cloud-native stack

long-range-arena. Long Range Arena for Benchmarking Efficient Transformers

quest_qa_labeling. Google QUEST Q&A Labeling. Improving automated understanding of complex question answer content

kaggle_tweet. Kaggle Tweet Sentiment Extraction Competition: 1st place solution (Dark of the Moon team)

onnxruntime. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

ConvBert. Python

RL-MMR. Code for "Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning", EMNLP 2020

TextAttack. TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

MHGRN. Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020)

tag-based-multi-span-extraction. The official implementation of EMNLP 2020, "A Simple and Effective Model for Answering Multi-span Questions".

self_talk. Code and data for the paper: "Unsupervised Common Sense Question Answering with Self-Talk"

KERMIT. 🐸 KERMIT - A lightweight library to encode and interpret Universal Syntactic Embeddings

low-resource-text-classification-framework. Research framework for low resource text classification that allows the user to experiment with classification models and active learning strategies on a large number of sentence classification datasets, and to simulate real-world scenarios. The framework is easily expandable to new classification models, active learning strategies and datasets.

abs_pretraining. Python

techqa. The TechQA dataset -- http://ibm.biz/Tech_QA

diseaseBERT. Code and dataset of EMNLP 2020 paper "Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition"

longformer. Longformer: The Long-Document Transformer

tf-explain. Interpretability Methods for tf.keras models with Tensorflow 2.x

interpret-text. A library that incorporates state-of-the-art explainers for text-based machine learning models and visualizes the result with a built-in dashboard.

interpretability-tutorial-emnlp2020. Materials for the EMNLP 2020 Tutorial on "Interpreting Predictions of NLP Models"

SelectiveMasking. Source code for "Train No Evil: Selective Masking for Task-Guided Pre-Training"

rasa. 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

ru-gpts. Russian GPT3 models.

FlexNeuART. Flexible classic and NeurAl Retrieval Toolkit

TensorPipe. High Performance Tensorflow Data Pipeline with State of Art Augmentations and low level optimizations.

TableBank. TableBank: A Benchmark Dataset for Table Detection and Recognition

recommenders. Best Practices on Recommendation Systems

sentence-transformers. State-of-the-Art Embeddings, Retrieval, and Reranking

docker-python. Kaggle Python docker image

models. Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

ERNIE. Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

language. Shared repository for open-sourced projects from the Google AI Language team.

kedro. Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.

MTM. MTM

mmner. Massively Multilingual Transfer for NER

pyod. A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

machine-learning-systems-design. A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`

clip-as-service. 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

uda. Unsupervised Data Augmentation (UDA)

tvm. Open Machine Learning Compiler Framework

Halide. a language for fast, portable data-parallel computation

TASO. The Tensor Algebra SuperOptimizer for Deep Learning

probability. Probabilistic reasoning and statistical analysis in TensorFlow

google-research. Google Research

PLMpapers. Must-read Papers on pre-trained language models.

ulmfit_keras. Keras wikipedia-based Language Model

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.

awd-lstm-lm. LSTM and QRNN Language Model Toolkit for PyTorch

TabNine. AI Code Completions

nni. An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

scipy. SciPy library main repository

kenlm. KenLM: Faster and Smaller Language Model Queries

scibert. A BERT model for scientific text.

nlpaug. Data augmentation for NLP

AutoPhrase. AutoPhrase: Automated Phrase Mining from Massive Text Corpora

LM-LSTM-CRF. Empower Sequence Labeling with Task-Aware Language Model

LightNER. Inference with state-of-the-art models (pre-trained by LD-Net / AutoNER / VanillaNER / ...)

SegPhrase. C++

AutoNER. Learning Named Entity Tagger from Domain-Specific Dictionary

multihead_joint_entity_relation_extraction. Implementation of our papers Joint entity recognition and relation extraction as a multi-head selection problem (Expert Syst. Appl, 2018) and Adversarial training for multi-context joint entity and relation extraction (EMNLP, 2018).

LSTM-ER. Implementation of End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures in ACL2016.

emnlp2017-relation-extraction. Context-Aware Representations for Knowledge Base Relation Extraction

tacred-relation. PyTorch implementation of the position-aware attention model for relation extraction

awesome-domain-adaptation. A collection of AWESOME things about domain adaptation

awesome-transfer-learning. Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)

awesome-quantum-machine-learning. Here you can get all the Quantum Machine learning Basics, Algorithms ,Study Materials ,Projects and the descriptions of the projects around the web

pytorch-acnn-model. code of Relation Classification via Multi-Level Attention CNNs

Relation-Classification-using-Bidirectional-LSTM-Tree. TensorFlow Implementation of the paper "End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures" and "Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths" for classifying relations

RESIDE. EMNLP 2018: RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

FewRel. A Large-Scale Few-Shot Relation Extraction Dataset

OpenNRE. An Open-Source Package for Neural Relation Extraction (NRE)

NREPapers. Must-read papers on neural relation extraction (NRE)

awesome-relation-extraction. 📖 A curated list of awesome resources dedicated to Relation Extraction, one of the most important tasks in Natural Language Processing (NLP).

bran. Full abstract relation extraction from biological texts with bi-affine relation attention networks

awesome-bert. bert nlp papers, applications and github resources, including the newst xlnet ， BERT、XLNet 相关论文和 github 项目

gpt-2. Code for the paper "Language Models are Unsupervised Multitask Learners"

eda_nlp. Data augmentation for NLP, presented at EMNLP 2019

awesome-annotation. List of online / computer-based annotation tools

kaggle_salt_bes_phalanx. Winning solution for the Kaggle TGS Salt Identification Challenge.

pytorch2keras. PyTorch to Keras model convertor

BERT-keras. Keras implementation of BERT with pre-trained weights

Russian-Language-Model. Jupyter Notebook

Kaggle-Carvana-3rd-Place-Solution. 3rd place solution ( Carvana Image Masking Challenge )

kaggle_carvana_segmentation. Code for the 1st place model in Carvana Image Masking Challenge

data_science_bowl_2018. My 5th place (out of 816 teams) solution to The 2018 Data Science Bowl organized by Booz Allen Hamilton

kaggle_2018_data_science_bowl_solution. 4th place solution for 2018 Data Science Bowl kaggle competition

DSB_2018. Python

2018DSB. 2018 Data Science Bowl 2nd Place Solution

dsb2018_topcoders. DSB2018 [ods.ai] topcoders

TGS-Salt-Identification. TGS Salt Identification

toxic. Toxic Comment Classification Challenge, 12th place solution https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge

KagglePlanetPytorch. 9th place solution for https://www.kaggle.com/c/planet-understanding-the-amazon-from-space

Kaggle-Planet-Understanding-the-Amazon-from-Space. 3rd place solution

pseudo_label_keras. Implementation of the pseudo-label algorithm with keras

Keras-RetinaNet-for-Open-Images-Challenge-2018. Code for 15th place in Kaggle Google AI Open Images - Object Detection Track

pytorch-saltnet. Kaggle | 9th place single model solution for TGS Salt Identification Challenge

argus-tgs-salt. Kaggle | 14th place solution for TGS Salt Identification Challenge

100-nlp-papers. 100 Must-Read NLP Papers

tqdm. :zap: A Fast, Extensible Progress Bar for Python and CLI

hyperopt. Distributed Asynchronous Hyperparameter Optimization in Python

test-tube. Python library to easily log experiments and parallelize hyperparameter search for neural networks

dtreeviz. A python library for decision tree visualization and model interpretation.

sacred. Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

catalyst. Accelerated deep learning R&D

LovaszSoftmax. Code for the Lovász-Softmax loss (CVPR 2018)

featuretools. An open source python library for automated feature engineering

awesome-monorepo. A curated list of awesome Monorepo tools, software and architectures.

Geospatial_Data_with_Python. Introduction to Geospatial Data with Python

selective_search_py. Python-based implementation of the Selective Search for Object Recognition.

autokeras. AutoML library for deep learning

TernausNet. UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

crfasrnn. This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vision/

unet. unet for image segmentation

salesforce-einstein-sentiment-analysis. Demo for Salesforce Einstein Sentiment Analysis (Natural Language Processing)

Image-OutPainting. 🏖 Keras Implementation of Painting outside the box

catboost. A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

bpemb. Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

sentencepiece. Unsupervised text tokenizer for Neural Network-based text generation.

NLP-progress. Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

kaggle-avazu. Code for the 3rd place finish for Avazu Click-Through Rate Prediction

ChatterBot. ChatterBot is a machine learning, conversational dialog engine for creating chat bots

gated_cnn. Keras implementation of “Gated Linear Unit ”

DeepPavlov. An open source library for deep learning end-to-end dialog systems and chatbots.

keras-contrib. Keras community contributions

NLP_Datasets. My NLP datasets for Russian language

anchor. Code for "High-Precision Model-Agnostic Explanations" paper

lime. Lime: Explaining the predictions of any machine learning classifier

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

jekyll. :globe_with_meridians: Jekyll is a blog-aware static site generator in Ruby

torch-rnn. Efficient, reusable RNNs and LSTMs for torch

char-rnn-tensorflow. Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

awesome-rnn. Recurrent Neural Network - A curated list of resources dedicated to RNN

awesome-computer-vision. A curated list of awesome computer vision resources

awesome-deep-vision. A curated list of deep learning resources for computer vision

convnetjs. Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

neuraltalk. NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

arxiv-sanity-preserver. Web interface for browsing, search and filtering recent arxiv submissions

testcontainers-scala. Docker containers for testing in scala

awesome-nlp. :book: A curated list of resources dedicated to Natural Language Processing (NLP)

fastText. Library for fast text representation and classification.

kafka. Apache Kafka - A distributed event streaming platform

pandas. Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

bazel. a fast, scalable, multi-language and extensible build system

conda. A system-level, binary package and environment manager running on all major operating systems and platforms.

kubernetes. Production-Grade Container Scheduling and Management