nlp

Fast and customizable framework for automatic ML model creation (AutoML)

The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.

🪐 End-to-end NLP workflows from prototype to production

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

Obsei is a low code AI powered automation tool. It can be used in various business flows like social listening, AI based alerting, brand image analysis, comparative study and more .

A persistent, network resilient, full text search library for the browser and Node.js

Persian NLP Toolkit

Korean BERT pre-trained cased (KoBERT)

Tribuo - A Java machine learning library

A multilingual dialog corpus

🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

🦙 Integrating LLMs into structured NLP pipelines

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

Developer friendly Natural Language Processing ✨

"結巴"中文分詞：做最好的 PHP 中文分詞、中文斷詞組件。 / "Jieba" (Chinese for "to stutter") Chinese text segmentation: built to be the best PHP Chinese word segmentation module.

Portfolio of data science projects completed by me for academic, self learning, and hobby purposes.

The most accurate natural language detection library for Go, suitable for short text and mixed-language text

NLP tools for Turkish.

Solves basic Russian NLP tasks, API for lower level Natasha projects

自然语言处理领域下的相关论文（附阅读笔记），复现模型以及数据处理等（代码含TensorFlow和PyTorch两版本）

An elegent pytorch implement of transformers

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.

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

🎓 系统性大语言模型构建课程｜🛠️ 覆盖预训练数据工程、Tokenizer、Transformer、MoE、GPU 编程 (CUDA/Triton)、分布式训练、Scaling Laws、推理优化及对齐 (SFT/RLHF/GRPO)｜🚀 6 个渐进式作业 + 代码驱动，建立 LLM 全栈认知体系

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).

ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Taranis AI is an advanced Open-Source Intelligence (OSINT) tool, leveraging Artificial Intelligence to revolutionize information gathering and situational analysis.

Videos, notes and experiments to understand deep learning