Coldison
Follow
Stars
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models'.
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowe…
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。
本项目是一个通过文字生成图片的项目，基于开源模型Stable Diffusion V1.5生成可以在手机的CPU和NPU上运行的模型，包括其配套的模型运行框架。
CLI for document conversion for scientific documents, powered by Mathpix OCR
Green Frog https://github.com/redleafnew/zotero-updateifs 的easyScholar数据版。更新影响因子，其他一系列工具，详见Readme
FinRL: Financial Reinforcement Learning. 🔥
A LaTeX beamer theme template for Tsinghua students.
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning 🔥 ⚡ 🌈
Awesome Chinese LLM: A curated list of Chinese Large Language Model 中文大语言模型数据集和模型资料汇总
Convert a PDDL domain into an OpenAI Gym environment.
AirLLM 70B inference with single 4GB GPU
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫
Tools and examples to export policies trained with Ray RLlib for lightweight and fast inference
实现了Baichuan-Chat微调，Lora、QLora等各种微调方式，一键运行。
搭建专属于你的消息推送服务，支持多种消息推送方式，支持 Markdown，基于 Golang 仅单可执行文件，开箱即用
RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，无须安装任何第三方agent库。
Awesome-LLM-Planning-Papers is a list of papers investigating and exploring the planning ablility of LLMs.
An Autonomous LLM Agent for Complex Task Solving
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].