contextualspellcheck
✔️Contextual word checker for better suggestions (not actively maintained)
uform
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
adapters
A Unified Library for Parameter-Efficient and Modular Transfer Learning
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
pytextclassifier
pytextclassifier is a toolkit for text classification. 文本分类,LR,Xgboost,TextCNN,FastText,TextRNN,BERT等分类模型实现,开箱即用。
detoxify
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
transformer-srl
Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.
nerpy
🌈 NERpy: Implementation of Named Entity Recognition using Python. 命名实体识别工具,支持BertSoftmax、BertSpan等模型,开箱即用。
efficient-task-transfer
Research code for "What to Pre-Train on? Efficient Intermediate Task Selection", EMNLP 2021
partial-embedding-matrix-adaptation
Vocabulary-level memory efficiency for language model fine-tuning.
tsdae
Tranformer-based Denoising AutoEncoder for Sentence Transformers Unsupervised pre-training.
automated-identification-of-security-relevant-configuration-settings-using-nlp
This repository is part of the paper "Automated Identification of Security-Relevant Configuration Settings Using NLP" accepted at the Industry Showcase track at the 37th IEEE/ACM International Conference on Automated Software Engineering (ASE). https://conf.researchr.org/track/ase-2022/ase-2022-industry-showcase.
banglasenti-dataset-prep
BanglaSenti Dataset Preparation: Bangla Sentiment Analysis CSV Dataset for NLP & Machine Learning