YAYI2
Multilingual model library
Develops large language models with high-quality multilingual data for various applications
YAYI 2 是中科闻歌研发的新一代开源大语言模型,采用了超过 2 万亿 Tokens 的高质量、多语言语料进行预训练。(Repo for YaYi 2 Chinese LLMs)
4k stars
7 watching
17 forks
Language: Python
last commit: 11 months ago artificial-intelligencechatchinesegptnatural-language-generationpretrained-language-modelyayi
Related projects:
Repository | Description | Stars |
---|---|---|
| Teaches Git version control in 30 days through a tutorial and personal experience | 4,004 |
| Automates interactions with WeChat using the ChatGPT API | 4,701 |
| A comprehensive platform for managing and testing APIs, providing features such as interface definition, testing, and deployment tools. | 27,448 |
| An LLM evaluation platform supporting various models and datasets | 4,295 |
| A language model designed to surpass the capabilities of GPT-3.5-Turbo on various tasks such as text generation, tool calling, and long-text processing | 7,209 |
| A proxy tool designed to bypass internet censorship and restrictions by disguising traffic as ordinary network activity. | 33,104 |
| Develops a deep-learning-based Chinese speech recognition system using TensorFlow and Keras. | 7,901 |
| A comprehensive video understanding toolbox and benchmark with modular design, supporting various tasks such as action recognition, localization, and retrieval. | 4,360 |
| A demo project showcasing integration with the OpenAI GPT-3.5 Turbo API for generating chatbot-like responses. | 8,014 |
| A collection of pre-trained language models for Chinese text processing and dialogue generation. | 3,034 |
| An online brain diagram editor tool with features such as cloud synchronization and shareable links. | 4,437 |
| Guides users to build applications using LangChain's framework and integrate it with Large Language Models (LLMs) for tasks like text generation, summarization, and search. | 7,533 |
| A Chinese language model developed to provide secure and reliable models for clients | 3,257 |
| A repository providing code and models for research into language modeling and multitask learning | 22,644 |
| Fine-tuned language models trained on mixed-quality data | 5,273 |