ArtificialIntelligence

An Autonomous LLM Agent for Complex Task Solving. Contribute to OpenBMB/XAgent development by creating an account on GitHub.

回答数 0，获得 8,987 次赞同

近段时间，ChatGPT 横空出世并获得巨大成功，使得 RLHF、SFT、IFT、CoT 等这些晦涩的缩写开始出现在普罗大众的讨论中。这些晦涩的首字母缩略词究竟是什么意思？为什么它们如此重要？我们调查了相关的所有重要论文…

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so. - LAION-AI/Open-Assistant: OpenAssistant is a c...

The field of artificial intelligence has made remarkable strides in recent years, particularly in the area of language modeling. One of the…

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices. - mlc-ai/mlc-llm: Enable everyone to develop, optimize and deploy AI models natively on everyone&am...

One embedder for all tasks

An open-source vector database for embedding similarity search and AI applications. - milvus-io/milvus: An open-source vector database for embedding similarity search and AI applications.

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Chinese medical dialogue data 中文医疗对话数据集. Contribute to Toyhom/Chinese-medical-dialogue-data development by creating an account on GitHub.

Bard 是为你提供创意启发和实用信息的好帮手。无论是激发想象力、提升工作效率，还是实现创意构想，Bard 都可助你一臂之力。

Build AI-powered applications with the latest AI language models

We are pleased to announce Claude 2, our newest model, which can be accessed via API as well as a new public-facing beta website at claude.ai.

We are excited to announce that our Chat API with RAG is now available in a public beta. With this new capability, developers can integrate user inputs, data sources, and model generations to build powerful product experiences and mitigate hallucinations by producing grounded and verifiable generations. The API is powered

Drag & drop UI to build your customized LLM flow using LangchainJS - FlowiseAI/Flowise: Drag & drop UI to build your customized LLM flow using LangchainJS

A series of large language models developed by Baichuan Intelligent Technology - baichuan-inc/Baichuan2: A series of large language models developed by Baichuan Intelligent Technology

百川智能以帮助大众轻松、普惠地获取世界知识和专业服务为使命，致力于通过语言AI的突破，构建中国最优秀的大模型底座。百川大模型，融合了意图理解、信息检索以及强化学习技术，结合有监督微调与人类意图对齐，在知识问答、文本创作领域表现突出。

**Few-Shot Learning** is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation. span class="description-source"Source: [Penalty Method for Inversion-Free Deep Bilevel Optimization ](https://arxiv.org/abs/1911.03432)/span

一、知识图谱嵌入知识图谱(KG)由一系列三元组的事实(h,r,t)构成，每个三元组中包含2个实体h和t及它们之间的关系r。KG的表示学习/嵌入：将关系和实体映射到一个低维连续空间上。其关键是定义三元组的打分函数，当事…

In this tutorial, we examine the Few-Shot Learning paradigm for deep and machine learning tasks. Readers can expect to learn what it is, different techniques, and details about use cases for Few-Shot Learning

Explore Few-Shot learning in computer vision, from foundational concepts to algorithms, including object detection nuances.