Official implementation for ICDAR 2021 best poster paper "Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer"

Python implementation of Elo-MMR as described in https://arxiv.org/abs/2101.00400

An open-source data logging library for machine learning models and data pipelines. 📚 Provides visibility into data quality & model performance over time. 🛡️ Supports privacy-preserving data collec…

Causal Impact but with MFLES and conformal prediction intervals

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

🐢 Open-Source Evaluation & Testing for LLMs and ML models

Foundational Models for State-of-the-Art Speech and Text Translation

Static Python call graph generator

An Open-source Toolkit for LLM Development

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

LLM vulnerability scanner

Google Research

Gorilla: An API store for LLMs

Seamlessly integrate LLMs into scikit-learn.

FinRL­-Meta: Dynamic datasets and market environments for FinRL.

This is the code for the "ChatGPT Trading Bot" Video by Siraj Raval on Youtube

Yeoman generator for building Microsoft Office related projects.

mRMR (minimum-Redundancy-Maximum-Relevance) for automatic feature selection at scale.

✨Fast Coreference Resolution in spaCy with Neural Networks

A collection of libraries to optimise AI model performances

[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...

The official implementation of CROMP (Constrained Regression with Ordered and Margin-sensitive Parameters) along with experimental test pipeline

Automatic extraction of relevant features from time series:

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

Efficient few-shot learning with Sentence Transformers

[EMNLP-Findings 2020] Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences

Question generation using state-of-the-art Natural Language Processing algorithms