happysalada Raphael Megzari

Tokenizer for Text to Speech (TTS) models

Triton Python client

Easily trim 'messages' arrays for use with GPTs

Fast BPE tokeniser for use with OpenAI's models

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

Python implementations of various stemming algorithms

System for quickly generating training data with weak supervision

Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores

Collection of BM25 Algorithms in Python

Library for unit extraction - fork of quantulum for python3

Python client for Qdrant vector search engine

Create Open XML PowerPoint documents in Python

Pytest plugin for parallel and concurrent testing

This module defines extensions to the standard “typing” module that are supported by the Pyre typechecker

Python SDK for Milvus

Python 3 Bindings for the NVIDIA Management Library

Simple client to fetch prompts from Prompt Hub using its REST API

Module for interacting with PostHog

Polygon is a python package that handles polygonal shapes in 2D

Pinecone Python SDK

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables

Convert PDF to DOCX

Machine Learning Framework from Industrial Practice

Multilingual OCR toolkits based on PaddlePaddle

ONNX Model Exporter for PaddlePaddle

Paddle numpy bfloat16 package

Transformers Model Optimization Tool of ONNXRuntime

ONNXMLTools enables conversion of models to ONNX

Dead-simple tool for executing Jupyter notebooks from the command line

Python module to read, parse and converting Microsoft Outlook MSG E-Mail files

Lucene query parser generating ElasticSearch queries

Use any LLM as a drop in replacement for gpt-3.5-turbo. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)

Utility package to create lazy modules, deferring associated imports until attribute access

Unified toolkit for Deep Learning Based Document Image Analysis

Standalone module for Locality-Aware NMS

Jinja2 extension to use humanize library inside jinja2 templates

Python library that provides common I/O interface across different storage backends

Package acting as a wrapper around the headless mode of existing web browsers to generate images from URLs and from HTML+CSS strings or files

LLM orchestration framework to build customizable, production-ready LLM applications

Standard Protobuf Reflection Service for gRPC

Standard Health Checking Service for gRPC

Channel Level Live Debug Information Service for gRPC

Collection of common code that's shared among different research projects in FAIR computer vision team

Open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena

More interactive weak supervision with FlyingSquid

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Facebook AI Research Sequence-to-Sequence Toolkit

PyTorch extensions for high performance and large scale training

Functional programming for Python

Universal Tensor Operations in Einstein-Inspired Notation for Python

PyTorch implementation of EfficientDet

SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications

APScheduler for Django

Random Name and Slug Generator

Standard data-centric AI package for data quality and machine learning with messy, real-world data and labels

Component orchestration engine

Compression AGSI middleware using brotli

Python port of Boilerpipe library

Read Google Cloud Storage, Azure Blobs, and local paths with the same interface

Open-source data curation platform for LLMs

Allure behave integration

Simple image hosting service

Optimism is Ethereum, scaled

Run open decision models locally behind a TypeSafe-compatible API

Orchestrate end-to-end encryption, cryptographic identities, mutual authentication, and authorization policies between distributed applications – at massive scale

Simple CLI for interacting with Google API authentication

Nushell plugin to query JSON, XML, and various web data

Nushell plugin to list system network interfaces