Projects sharing features with MITIE

Starspace is a vector embedding framework designed for training high-dimensional representations of text and images. It functions as a machine learning system for neural ranking, text classification, and knowledge graph embedding, mapping different object types into a shared numerical space to facilitate retrieval and prediction tasks. The system includes specialized tools for knowledge graph completion and link prediction by representing entities and their relationships within a multi-relational vector space. It further provides capabilities for semantic content recommendation and large-scal

BLLIP reranking parser (also known as Charniak-Johnson parser, Charniak parser, Brown reranking parser) See http://pypi.python.org/pypi/bllipparser/ for Python module.

A Modern C++ Data Sciences Toolkit

GraphGPT is an LLM knowledge graph generator that extracts entities and relationships from unstructured text to create visual knowledge graphs. It functions as a natural language graph interface and an unstructured data extraction pipeline, transforming raw text into structured triples for mapping complex information networks. The system enables dynamic knowledge mapping by allowing users to build and update network visualizations through conversational queries and text-based instructions. This allows for the conversion of unstructured data into visual graphs to identify patterns and connecti

Transformers Tasks is a collection of toolkits and scripts dedicated to language model fine-tuning, natural language processing tasks, and transformer-based pipelines. The project functions as a natural language processing toolkit and transformer pipeline library, providing Python scripts and algorithms designed to adapt foundational language models and route text inputs through modular processing workflows. The repository covers supervised fine-tuning pipelines and reinforcement learning alignment procedures that optimize generative text outputs through reward modeling and policy gradient lo

OpenNRE is a natural language processing library and neural relation extraction framework designed to transform unstructured text into structured relational data. It serves as a toolkit for identifying relationship types between entities and generating entity-relation-entity triples to populate and expand knowledge bases. The framework provides tools for both supervised and distantly supervised relation extraction, allowing neural models to be trained on labeled datasets or via automated pipelines that align knowledge base triples with raw text. The project covers a full information extracti

Entity-Relation-Extraction is a machine learning framework designed to identify entities and their logical connections within unstructured text. It functions as a pipeline that transforms raw documents into structured knowledge graphs by utilizing deep learning models and transformer architectures. The project distinguishes itself through a schema-driven approach, which maps extracted information to predefined relational templates to ensure output consistency. It employs a multi-stage process that combines sequence-labeling token classification with contextual encoding to delineate entity bou

Multilingual text (NLP) processing toolkit

Chat with your favourite LLaMA models in a native macOS app

AudioGPT is an LLM-driven audio framework and processing suite that uses large language models to orchestrate neural audio pipelines. It functions as a multimodal audio generator and processing system, integrating a collection of pretrained models to handle speech synthesis, sound generation, and audio manipulation. The system is distinguished by its ability to generate audio from diverse inputs, including text and images, and its capacity to produce synchronized talking head videos. It also operates as a neural speech translator, converting spoken language between different tongues while pre

Gibran is an Elixir natural language processor, and a port of WordsCounted.

Simple sentiment analysis with Ruby

This repository contains custom pipes and models related to using spaCy for scientific documents.

ChatALL is a desktop application that functions as a multi-model chat client and aggregator for artificial intelligence services. It enables users to send a single prompt to multiple AI models simultaneously, allowing for the side-by-side comparison of generated responses within a unified interface. The application distinguishes itself through a local-first approach to data management, ensuring that all conversation logs and user configurations are stored directly on the user's device. This architecture supports privacy and offline access while providing a centralized system for managing and

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Summary of Responses to Questionnaire on Annotation Platform https://forms.gle/iZk8kehkjAWmB8xe9

This repository consists of all my NLP Projects

DocsGPT is a retrieval-augmented generation platform and private knowledge base used to build AI agents that perform grounded search and analysis. It functions as a multi-model AI orchestrator and enterprise agent builder, allowing for the integration of various local and cloud language models to customize reasoning and text generation. The project provides a visual environment for developing automated assistants using conditional logic and third-party API connectivity. It enables the creation of private AI agents capable of performing enterprise search and detailed document analysis using pr

Argilla is a collaborative AI feedback tool and data curation management system. It serves as a human-in-the-loop dataset platform designed to coordinate workforce annotators and domain experts in labeling, rating, and refining data samples for machine learning projects. The platform focuses on large language model dataset curation and reinforcement learning from human feedback workflows. It provides a shared workspace for integrating human expertise into AI development to validate model outputs and correct data errors. The system manages the end-to-end machine learning data pipeline, includ

Implementation of various topic models

lecture notes for probabilistic topic models using ipython notebook

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

A Multilingual Latent Dirichlet Allocation (LDA) Pipeline with Stop Words Removal, n-gram features, and Inverse Stemming, in Python.

AllenNLP is a PyTorch-based research library and deep learning language toolkit designed for developing and training neural network architectures for linguistic tasks. It provides a distributed training system that coordinates data and gradients across multiple GPUs and a framework for integrating pretrained transformer architectures. The system distinguishes itself with a dedicated algorithmic bias mitigation tool used to identify and reduce bias in linguistic model predictions. It also includes model influence analysis to interpret predictions by calculating the influence of specific traini