Prithivida

Gramformer. A framework for detecting, highlighting and correcting grammatical errors on natural language text. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

FlashRank. Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

Parrot_Paraphraser. A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

Styleformer. A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual, active/passive, and many more. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

Route0x. Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da

ZSIC. Zero Shot Image Classification but more, Supports Multilingual labelling and a variety of CNN based models for a vision backbone by using OpenAI CLIP for $ conscious uses (Super simple, so a 10th-grader could totally write this but since no 10th-grader did, I did) - Prithivi Da

Alt-ZSC. Alternate Implementation for Zero Shot Text Classification: Instead of reframing NLI/XNLI, this reframes the text backbone of CLIP models to do ZSC. Hence, can be lightweight + supports more languages without trading-off accuracy. (Super simple, a 10th-grader could totally write this but since no 10th-grader did, I did) - Prithivi Da

SPLADERunner. Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.

blitz-embed. C++ inference wrappers for running blazing fast embedding services on your favourite serverless like AWS Lambda. By Prithivi Da, PRs welcome.

NLP-Experiments. NLP related python solutions and recipes I built

vision-language-modelling-series. Companion Repo for the Vision Language Modelling YouTube series - https://bit.ly/3PsbsC2 - by Prithivi Da. Open to PRs and collaborations

MQTTPush4Android. MQTT Push Notification Service for Android

Applied-ML-from-1st-principles. Companion Repo for the book The Applied ML Field Manual, Prithiviraj Damodaran

flashembed. Lightweight Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines.

RealTimeNotification. AWS SNS Equivalent - LMAX Disruptor/MQTT/RabbitMQ/ based Real-time x-Platform Notification Framework

KeyBERT. Minimal keyword extraction with BERT

WhatTheFood. An intentionally simple Image to Food cross-modal search. Created by Prithiviraj Damodaran.

lateness. A ModernColBERT lib that allows you to do 1.) Cheap and lightweight retrieval and 2.) heavy GPU accelerated indexing into vectorDBs that offers native multi-vector support like Qdrant, Vespa and more..

AirportTaxiDemandPrediction. Airport Taxi Demand Forecast ML problem

Speech-Recognition. This repository contains the code for the speech recognition in python

langid-benchmark. A benchmark of off-the-shelf models that detects language in text - Contributions welcome

VisionLanguageProgress. Repository to track the progress in V+L Multimodal Learning, including the datasets and the state-of-the-art of the current pre-trained models on various V+L tasks

C4_200M-synthetic-dataset-for-grammatical-error-correction. This dataset contains synthetic training data for grammatical error correction. The corpus is generated by corrupting clean sentences from C4 using a tagged corruption model. The approach and the dataset are described in more detail by Stahlberg and Kumar (2021) (https://www.aclweb.org/anthology/2021.bea-1.4/)

Whatsapp--. A variant of whatsapp called "whatsapp--" with cassandra

JointBERT. Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"

Condenser. EMNLP 2021 - Pre-training architectures for dense retrieval

PIE. Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)

ICECAGE. Image CEntric CAption Generation Evaluation

sentence-transformers. Multilingual Sentence & Image Embeddings with BERT

PrithivirajDamodaran.

async-http-client. Asynchronous Http and WebSocket Client library for Java

py-readability-metrics. 📗 Score text readability using a number of formulas: Flesch-Kincaid Grade Level, Gunning Fog, ARI, Dale Chall, SMOG, and more

IndeedSalaryPrediction. Indeed Salary Prediction

ATMFraudMonitor. CEP for Banking systems powered by Apache Flink

bias-bench. Extension of bias-bench for select Sentence Transformers* models

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

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

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

bert-gec. Shell

llama.cpp. LLM inference in C/C++