Starred repositories
支持word(.docx)、excel(.xlsx,.xls)、pdf、pptx等各类型office文件预览的vue组件集合,提供一站式office文件预览方案,支持vue2和3,也支持React等非Vue框架。Web-based pdf, excel, word, pptx preview library
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Run safety benchmarks against AI models and view detailed reports showing how well they performed.
Huly — All-in-One Project Management Platform (alternative to Linear, Jira, Slack, Notion, Motion)
Scrapy, a fast high-level web crawling & scraping framework for Python.
This is the official Pytorch implementation of Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models.
S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models
Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.
Convert PDF to markdown + JSON quickly with high accuracy
markdown2: A fast and complete implementation of Markdown in Python
A fast yet powerful Python Markdown parser with renderers and plugins.
A fast, extensible and spec-compliant Markdown parser in pure Python.
Create and modify Word documents with Python
A library to extract the main content from html. Developed for information on LLM and for feeding data into LangChain and LlamaIndex.
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
Set of tools to assess and improve LLM security.
[ECCV2024] This is an official inference code of the paper "Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering" and "Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Mu…