摘要:
OS-Copilot https://github.com/OS-Copilot/OS-Copilot An self-improving embodied conversational agent seamlessly integrated into the operating system to 阅读全文
摘要:
minio https://github.com/minio/minio MinIO 是在 GNU Affero 通用公共许可证 v3.0 下发布的对象存储系统。它与 Amazon S3 云存储服务兼容 API。它能够处理非结构化数据,例如照片、视频、日志文件、备份和容器图像,支持的最大对象大小为 阅读全文
摘要:
agentscope https://doc.agentscope.io/en/index.html Welcome to AgentScope Tutorial AgentScope is an innovative multi-agent platform designed to empowe 阅读全文
摘要:
流服务器项目 https://github.com/tiangolo/nginx-rtmp-docker https://github.com/search?q=nginx%20rtmp&type=repositories RTSP 和 RTMP原理&推拉流 https://blog.csdn.ne 阅读全文
摘要:
yolov5 https://github.com/ultralytics/yolov5 对rtsp视频流的支持 https://github.com/ultralytics/yolov5/blob/master/detect.py @smart_inference_mode() def run( 阅读全文
摘要:
Top 100+ Generative AI Applications / Use Cases in 2024 https://research.aimultiple.com/generative-ai-applications/#general-generative-ai-applications 阅读全文
摘要:
360智脑 https://aiot.360.cn/solutions/factory https://zhuanlan.zhihu.com/p/633755589 1、开放目标检测:自然语言输入快速完成数据标注 一些安防巡店场景下,摄像头会出现被遮挡、发生偏移、镜头对向室外等人为干扰现象,因此,3 阅读全文
摘要:
LVM https://yutongbai.com/lvm.html https://zhuanlan.zhihu.com/p/671423679 Large Vision Model(简称LVM)是一种纯粹基于视觉数据进行训练和推理的大型模型,其特点在于无需涉及任何自然语言输入或输出。该模型的提出 阅读全文
摘要:
llm overview https://research.aimultiple.com/llmops-tools/ integration framework is our target. Architecture -- llm-app-stack https://github.com/a16z- 阅读全文
摘要:
面向真实监控场景的多模态视频理解 https://mp.weixin.qq.com/s/3iPeKtqVEKvWpOb_pqEOXA 3. 多模态异常检测 在监控视频领域,常用到多模态异常检测这一技术。传统的异常检测主要关注视频画面的大规模变化或异常行为,如打架或车祸等。随着技术进步,特别是 GPT 阅读全文
摘要:
RAG OVERVIEW https://opendatascience.com/getting-started-with-multimodal-retrieval-augmented-generation/ What is RAG? RAG is an architectural framewor 阅读全文
摘要:
https://www.cnblogs.com/88223100/p/LangChain-the-hottest-LLM-application-development-framework-for-beginners.html 以 GPT 模型为例: 1.数据滞后,现在训练的数据是到 2021 年 阅读全文
摘要:
大模型的能力来源 https://arxiv.org/pdf/2402.18041 大模型合规来源 https://arxiv.org/html/2402.12193v2 大模型的罪恶检测来源 https://www.kaggle.com/datasets/odins0n/ucf-crime-dat 阅读全文
摘要:
Phi-2: The surprising power of small language models https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models 阅读全文
摘要:
Pixtral 12B - the first-ever multimodal Mistral model. https://mistral.ai/news/pixtral-12b/ Pixtral 12B in short: Natively multimodal, trained with in 阅读全文
摘要:
python_package https://github.com/fanqingsong/python_package Description A production ready python library template Metadata and dependency informatio 阅读全文
摘要:
MoneyPrinterTurbo https://github.com/harry0703/MoneyPrinterTurbo/tree/main 利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM. FunCli 阅读全文
摘要:
crewAI-examples github demo 文生图 完成读取文章,配图,发tweet。 https://github.com/wassim249/xgrow/blob/master/main.py#L23 文生图 https://github.com/coderphonui/crewai 阅读全文
摘要:
autoGPT metagpt crewAI langgraph autogen camel 哪些框架适用于多模态场景? 特点:CrewAI是一个专门用于创建多模态代理的技术,能够同时处理文本、图像和音频数据。它提供了构建多模态代理所需的工具和库,使得开发者能够更容易地集成不同模型以处理多种数据类型 阅读全文
摘要:
Zero-Shot,One-Shot,Few-Shot,In-Context Learning https://blog.csdn.net/weixin_44212848/article/details/139902394 In-Context Learning定义:In-context learn 阅读全文
摘要:
awesome-ai-agents https://datawhalechina.github.io/hugging-multi-agent/chapter2/AIAgent%E7%9F%A5%E8%AF%86%E4%BD%93%E7%B3%BB%E7%BB%93%E6%9E%84/#213-sy1 阅读全文
摘要:
Large Multimodal Agents: A Survey https://arxiv.org/pdf/2402.15116 阅读全文
摘要:
Comparing Multi-agent AI frameworks https://sajalsharma.com/posts/overview-multi-agent-fameworks/ A Comparative Overview To better understand the diff 阅读全文
摘要:
Retrying library for Python https://github.com/jd/tenacity Please refer to the tenacity documentation for a better experience. Tenacity is an Apache 2 阅读全文
摘要:
ReAct https://learnprompting.org/docs/advanced_applications/react What is ReAct? ReAct1 (Reason + Act) is a paradigm that enables language models to s 阅读全文
摘要:
Agentic Design Patterns https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/?ref=dl-staging-website.ghost.io Reflection: The 阅读全文
摘要:
Efficient DevSecOps Workflows with a Little Help from AI https://www.infoq.com/articles/efficient-devsecops-workflows/ AI is enhancing DevSecOps workf 阅读全文
摘要:
GGUF大模型文件格式 https://www.datalearner.com/blog/1051705718835586 大语言模型的开发通常使用PyTorch等框架,其预训练结果通常也会保存为相应的二进制格式,如pt后缀的文件通常就是PyTorch框架保存的二进制预训练结果。 但是,大模型的存储 阅读全文
摘要:
ragflow https://github.com/infiniflow/ragflow RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understandi 阅读全文
摘要:
overview publisher name 支持图片 支持视频 github 测试网址 COMMENT OpenGVLab InternVL YES https://github.com/OpenGVLab/InternVL https://internvl.opengvlab.com/ Ope 阅读全文
摘要:
Base/chat/instruct https://blog.csdn.net/qq_43127132/article/details/140447880 大模型库中的base、chat、instruct和4bit通常指的是不同类型或配置的预训练语言模型。它们的区别主要在于训练目标、用途和模型参数 阅读全文
摘要:
支持能力 https://arxiv.org/pdf/2402.06196 能力增强方法 当我们谈论大模型时,应该关注哪些新能力? https://www.thepaper.cn/newsDetail_forward_22829654 能力一:涌现能力(emergent abilities) 涌现能 阅读全文
摘要:
MiniCPM https://github.com/OpenBMB/MiniCPM 面壁智能推出的大模型,在如下方面支持能出众。 推理 长文本 RAG 都是常见的能力。 其中 指令遵从(IF=instruction follow) 和 工具调用(FC = function call), 威力强大, 阅读全文
摘要:
Transformer (language) https://www.cnblogs.com/kongen/p/18088002 https://www.infoq.cn/article/qbloqm0rf*sv6v0jmulf https://arxiv.org/pdf/2402.06196 ht 阅读全文
摘要:
data-analysis-llm-agent https://github.com/fanqingsong/data-analysis-llm-agent Conversational AI with Function Calling for Data Analysis Overview The 阅读全文
摘要:
华为 huawei-eyewear-2 https://consumer.huawei.com/cn/audio/huawei-eyewear-2/ https://new.qq.com/rain/a/20240515A06AXH00 续航11小时, 连接华为手机和平板 语音助手、播放音乐、接挂电话 阅读全文
摘要:
多模态大模型(MLLMs)是一类结合了大型语言模型(LLMs)的自然语言处理能力与对其他模态(如视觉、音频等)数据的理解与生成能力的模型。 旨在通过整合文本、图像、声音等多种类型的输入和输出,提供更加丰富和自然的交互体验。 A Survey on Multimodal Large Language 阅读全文
摘要:
TensorFlow Lite https://tensorflow.google.cn/lite Deploy machine learning models on mobile and edge devices TensorFlow Lite is a mobile library for de 阅读全文
摘要:
operators https://github.com/Tencent/ncnn/blob/master/docs/developer-guide/operators.md AbsVal ArgMax BatchNorm Bias BinaryOp BNLL Cast CELU Clip Conc 阅读全文
摘要:
Object Detection: Non-Maximum Suppression (NMS) https://kikaben.com/object-detection-non-maximum-suppression/ Object detection models like YOLOv5 and 阅读全文