Software company specializing in developer tools and tailored solutions for AI and Natural Language Processing
79
Dépôts publics
57 166
Total des étoiles
1 488
Abonnés
Explosion est une organisation basée à Berlin, spécialisée dans les outils de développement et les solutions sur mesure pour l'intelligence artificielle et le traitement du langage naturel. Sur GitHub, explosion maintient une large gamme de dépôts publics, principalement en Python, Cython et JavaScript, comprenant des projets notables tels que spaCy et thinc.
💫 Industrial-strength Natural Language Processing (NLP) in Python
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
👩🏫 Advanced NLP with spaCy: A free online course
💫 Models for the spaCy Natural Language Processing (NLP) library
🦆 Contextually-keyed word vectors
🪐 End-to-end NLP workflows from prototype to production
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
🦙 Integrating LLMs into structured NLP pipelines
📚 Process PDFs, Word documents and more with spaCy
🤖 A PyTorch library of curated Transformer models and their composable components
👑 spaCy building blocks and visualizers for Streamlit apps
💥 Use the latest Stanza (StanfordNLP) research models directly in spaCy
🍳 Recipes for the Prodigy, our fully scriptable annotation tool
🦉 Modern high-performance serialization utilities for Python (JSON, MessagePack, Pickle)
🍣 A lightweight console printing and formatting toolkit
💥 Cython memory pool for RAII-style memory management
:boom: displaCy.js: An open-source NLP visualiser for the modern web
🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy
✨ Bootstrap annotation with zero- & few-shot learning via OpenAI GPT-3
🌓 Bringing pjreddie's DarkNet out of the shadows #yolo
💫 Jupyter notebooks for spaCy examples and tutorials
💫 REST microservices for various spaCy-related tasks
💥 Fast matrix-multiplication as a self-contained Python library – no system dependencies!
:boom: displaCy-ent.js: An open-source named entity visualiser for the modern web
Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/
:candy: Confection: the sweetest config system for Python
🧬 A JupyterLab extension for annotating data with Prodigy
Super lightweight function registries for your library
💙 Emoji handling and meta data for spaCy with custom extension attributes
🎡 Automated build repo for Python wheels and source packages
💫 Scripts, tools and resources for developing spaCy
📂 Additional lookup tables and data resources for spaCy
🕊️ Radically lightweight command-line interfaces
🧪 Cutting-edge experimental spaCy components and features
🍏 Make Thinc faster on macOS by calling into Apple's native Accelerate library
🦦 weasel: A small and easy workflow system
💥 Browser-based slides or PDFs of our talks and presentations
Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.
💥 Cython hash tables that assume keys are pre-hashed
pkuseg多领域中文分词工具; The pkuseg toolkit for multi-domain Chinese word segmentation
💥 Use Hugging Face text and token classification pipelines directly in spaCy
☄️ Parallel and distributed training with spaCy and Ray
💥 Cython bindings for MurmurHash2
🌊 Machine learning dataset loaders for testing and example scripts
🤗 Push your spaCy pipelines to the Hugging Face Hub
💥 Explosion Assets
Generate a SQLite database from Wikipedia & Wikidata dumps.
A Prodigy plugin for PDF annotation
💫 A spaCy package for Yohei Tamura's Rust tokenizations library
spaCy entry points for Curated Transformers
spaCy extension for Visual Studio Code
🧬 A VS Code extension for annotating data with Prodigy
Train huggingface models on top of Prodigy annotations
💫 Runtime performance comparison of spaCy against other NLP libraries
Wrapper for the macOS signpost API
🌸 Train floret vectors
A slightly cleaned up version of the scripts & data for the CoNLL 2012 Coreference task.
🔎 A Prodigy plugin for evaluating spaCy pipelines
Lightweight piece tokenization library
📟 Logging utilities for spaCy
Select pixels in Prodigy via Facebook's Segment-Anything model.
🔮 GPU kernels for Thinc
A Prodigy pluging for ANN techniques
Audio transcription with OpenAI's whisper model in the loop.
🕸️ Legacy architectures and other registered spaCy v3.x functions for backwards-compatibility
Code for our presentation in Princeton DH 2023 April.
A Prodigy plugin for document search via LUNR
Aucune description fournie pour ce dépôt.
Aucune description fournie pour ce dépôt.
:octocat: GitHub settings
Loaders for various span labeling datasets
Aucune description fournie pour ce dépôt.
Materials for the aiGrunn 2023 talk on spaCy Transformer pipelines
📒 Repository used to build Binder images for the interactive spaCy code examples
BLAS-like Library Instantiation Software Framework
Terraform definitions for self-hosted Ellf clusters
Aucune description fournie pour ce dépôt.
Add-ons for Curated Transformers
Nginx container that allows for environmental variable use to set nginx configuration.
Explosion développe des outils et des bibliothèques pour le traitement du langage naturel, avec des projets notables comme spaCy, thinc et sense2vec. Ces dépôts sont conçus pour aider les développeurs dans leurs projets d'intelligence artificielle.
Explosion utilise principalement Python pour ses projets, mais également Cython, Jupyter Notebook, C++, C et JavaScript. Ces langages permettent de créer des solutions adaptées aux besoins des utilisateurs en matière de traitement du langage naturel.
Oui, tous les dépôts d'explosion sur GitHub sont publics. Cela permet à la communauté des développeurs d'accéder aux ressources, de contribuer et d'utiliser des outils tels que spaCy et d'autres projets pour leurs propres applications.
Surveillez Explosion avec RepoGuard et soyez alerté dès qu'un nouveau dépôt public apparaît.
Surveiller ce compte