abelriboulot / onnxt5
Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
☆252Updated 2 years ago
Alternatives and similar repositories for onnxt5:
Users that are interested in onnxt5 are comparing it to the libraries listed below
- Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.☆126Updated 4 years ago
- ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.☆574Updated last year
- Making BERT stretchy. Semantic Elasticsearch with Sentence Transformers☆159Updated 4 years ago
- xfspell — the Transformer Spell Checker☆188Updated 4 years ago
- New dataset☆303Updated 3 years ago
- XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale☆153Updated last year
- Interpretable Evaluation for (Almost) All NLP Tasks☆195Updated 2 years ago
- This repository contains the code for "Generating Datasets with Pretrained Language Models".☆188Updated 3 years ago
- EMNLP 2020: "Dialogue Response Ranking Training with Large-Scale Human Feedback Data"☆337Updated 4 months ago
- Builds wordpiece(subword) vocabulary compatible for Google Research's BERT☆229Updated 4 years ago
- Simple State-of-the-Art BERT-Based Sentence Classification with Keras / TensorFlow 2. Built with HuggingFace's Transformers.☆199Updated 9 months ago
- The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model Fine-tuning" https://arxiv.org/abs/1909.04761☆283Updated 4 years ago
- LASER multilingual sentence embeddings as a pip package☆224Updated last year
- An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/p…☆430Updated 2 years ago
- ⛔ [NOT MAINTAINED] A web-based annotator for closed-domain question answering datasets with SQuAD format.☆88Updated 2 years ago
- Question Answering using Albert and Electra☆206Updated last year
- Google USE (Universal Sentence Encoder) for spaCy☆182Updated last year
- TyDi QA contains 200k human-annotated question-answer pairs in 11 Typologically Diverse languages, written without seeing the answer and …☆301Updated 4 years ago
- Repository for the paper "Optimal Subarchitecture Extraction for BERT"☆471Updated 2 years ago
- Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive…☆429Updated last year
- Scripts and links to recreate the ELI5 dataset.☆324Updated 3 years ago
- Language-agnostic BERT Sentence Embedding (LaBSE)☆147Updated 4 years ago
- NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT☆231Updated last year
- Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.☆102Updated 2 years ago
- ☆66Updated 4 years ago
- Forte is a flexible and powerful ML workflow builder. This is part of the CASL project: http://casl-project.ai/☆243Updated last year
- Semantic search using Transformers and others☆110Updated 4 years ago
- code and supplementary materials for a series of Medium articles about the BERT model☆77Updated last year
- This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, an…☆556Updated 3 years ago
- Code for obtaining the Curation Corpus abstractive text summarisation dataset☆125Updated 4 years ago