texar
FreeToolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/
About texar
Texar is a highly modularized and customizable toolkit for machine learning, natural language processing, and text generation. It supports both TensorFlow (Texar-TF) and PyTorch (Texar-PyTorch) with comprehensive modules for data processing, model architectures, loss functions, training and inference algorithms, and evaluation. Texar allows users to compose arbitrary models and algorithms with high-level APIs that reduce boilerplate code.
Key Features
Pros & Cons
- Highly modular and customizable
- Supports both major deep learning frameworks (TensorFlow and PyTorch)
- Comprehensive modules covering full ML workflow
- High-level APIs reduce boilerplate code
- Actively maintained as part of the ASYML project
Best For
Alternatives to texar
CDial-GPT
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
ChatLM-mini-Chinese
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
Chat-Haruhi-Suzumiya
Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.
DialoGPT
Large-scale pretraining for dialogue
GPT2-Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
gpt-2-simple
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts