Stars
电子邮件是一款简化的具备邮件服务器的企业邮箱,支持在将其他主流邮箱的邮件进行导入后自主控制邮件数据安全。电子邮件以其简洁精确的功能和小巧安全的架构方便根据企业和政府机构的业务要求进行二次开发。电子邮件是一个完全开源的项目,无商业版,但是需要依赖开源的数字底座进行人员岗位管控。
Open Source three.js cesium.js examples and demo community - 开源的 three.js 和 cesium.js 案例社区 ---- star ----点星星
Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.
An acceleration library that supports arbitrary bit-width combinatorial quantization operations
4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions
MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
[EMNLP 2024 Findings] Official PyTorch Implementation of "Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation"
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins
A powerful library for parsing on-chain transactions into clear, human-readable actions, streamlining blockchain data analysis and interpretation. 🐋
3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion
A comprehensive survey on Internal Consistency and Self-Feedback in Large Language Models.
Python implementation of Remez algorithm, provides the best uniform polynomial approximation to functions based on the minimization of the maximum absolute error and the equioscillation theorem.
⭐ Dynamically generate stats SVG from your Github, LeetCode, Steam, and more in #Cyberpunk style :)
Effortlessly solve LeetCode problems with the power of automation! LeetCode Solver Bot automates fetching problems, generating solutions, debugging, and submission. No more manual coding or debuggi…
A React based chat rich text component
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
This is the official reproduction of FancyVideo.
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-spee…
A framework to build GUI-like Agent Tools, enhancement to Function Calling of LLM AI.
数据标注是一款专门对文本数据进行处理和标注的工具,通过简化快捷的文本标注流程和动态的算法反馈,支持用户快速标注关键词并能通过算法持续减少人工标注的成本和时间。数据标注的过程先由人工标注构筑基础,再由自动标注反哺人工标注,最后由人工标注进行纠偏,从而大幅度提高标注的精准度和高效性。数据标注是一个完全开源的项目,无商业版,但是需要依赖开源的数字底座进行人员岗位管控。各类词库结果会定期在本平台公开。
工作流引擎对内提供单位/机关流程管理规则和内部业务流程的数字化落地实践;对外提供自动化地第三方业务驱动、接口接入和算法单元驱动能力。工作流引擎在提供底层驱动引擎的同时对全局透明监控、安全防御和国产化特色功能进行充分考虑,是内部流程管理和业务算法驱动的不二之选。
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Propensity Score Matching(PSM) on python