word2vec implementation

FastText for Node.js

Stand-alone Language Identification for Node.js JavaScript based on FastText

TensorFlow Lite Erlang bindings with optional EdgeTPU support.

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Library for fast text representation and classification.

locality sensitive hashing (LSHASH) for Python3

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

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Self-Supervised Document-to-Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference

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.

code for the paper "Cluster & Tune: Boost Cold Start Performance in Text Classification" for ACL2022

Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep RL Workshop) and "Accelerating Neural Self-Improvement via Bo…

LUKE -- Language Understanding with Knowledge-based Embeddings

Experiments with Hugging Face 🔬 🤗

Autoregressive Entity Retrieval

This repository contains the code for the paper 'PARM: Paragraph Aggregation Retrieval Model for Dense Document-to-Document Retrieval' published at ECIR'22.

Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022

FastText Pytorch version

Implementation of State-of-the-art Text Classification Models in Pytorch

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"

Easily compute clip embeddings and build a clip retrieval system with them

Automatically create Faiss knn indices with the most optimal similarity search parameters.

fastText Rust binding

fastText model serving service

ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost

Search Engines with Autoregressive Language models