A PyTorch implementation of an Adaptive Memory Multi-Batch L-BFGS

Implementation of the GBST block from the Charformer paper, in Pytorch

Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch

Source code for "N-ary Constituent Tree Parsing with Recursive Semi-Markov Model" published at ACL 2021

Simple and extensible administrative interface framework for Flask

Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021. It is based on our NERE toolkit (https://github.com/Receiling/NERE).

Caucasus languages focused multilingual and monolingual corpuses for Natural Language Processing(NLP)

SemClinBr - a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks

Active Learning for Text Classification in Python

Must-read papers on prompt-based tuning for pre-trained language models.

Extract main body text from HTML (HTMLから本文を抽出)

A text augmentation tool for named entity recognition.

Code for "Dynamic Contextualized Word Embeddings"

Unofficial faiss wheel builder

A *tuned* minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Implementation of Multistream Transformers in Pytorch

🚀 efficient approximate nearest neighbor search algorithm collections library written in Rust 🦀 .

A library for multi-class and multi-label classification

Official implementation of "Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path" (ACL'21)

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).

[ACL-IJCNLP 2021] Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

Source code of ACL2022 "Headed-Span-Based Projective Dependency Parsing" and "Combining (second-order) graph-based and headed-span-based projective dependency parsing

Simple Python library for doing (multiple) sequence alignment

Implementation of Fast Transformer in Pytorch

Active Learning Transformers

Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.

Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper

SSDB - A fast NoSQL database, an alternative to Redis

Hierarchical multi-label text classification of the BlurbGenreCollection using capsule networks.