Simple demonstration of a cjk tokenizer.

An experimental open-source attempt to make GPT-4 fully autonomous.

Example models using DeepSpeed

A fast JSON parser/generator for Java.

UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

The official tool for creating proceedings for conferences of the Association for Computational Linguistics (ACL).

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.

Unicoder model for understanding and generation.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Must-read Papers on pre-trained language models.

bert nlp papers, applications and github resources, including the newst xlnet ， BERT、XLNet 相关论文和 github 项目

Personal website powered by Jekyll

Converting A PyTorch Model to Tensorflow pb using ONNX

The dataset and code for the paper "Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information"

✏️ Neural Style Transfer: A Review

The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.

python版本：领域细分的中文分词工具，简单易用，跟现有开源工具相比提高了分词的准确率。

镜像：https://coding.net/u/scaffrey/p/hosts/git

VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social …

A TensorFlow Implementation of the Transformer: Attention Is All You Need