关键词 "r1" 的搜索结果, 共 24 条, 只显示前 480 条
Open-source AI model excelling in reasoning and coding tasks.
Transforms text into stunning AI art.
AI gaming buddy with Tyler1 vibes
MAI-DS-R1 是 DeepSeek-R1 推理模型,经过微软 AI 团队的后期训练,提高了其对受阻主题的响应能力和风险状况,同时保持了其推理能力和竞争性能。基于 DeepSeek-R1,这是一种基于 Transformer 的自回归语言模型,利用多头自注意力和混合专家 (MoE) 进行可扩展和高效的推理。 MAI-DS-R1 是一个 DeepSeek-R1 推理模型,经过微软 AI 团
QwQ 是 Qwen 系列的推理模型。与传统的指令调优模型相比,QwQ 具备思考和推理能力,在下游任务,尤其是难题中能够取得显著的性能提升。QwQ-32B 是中型推理模型,其性能足以匹敌 DeepSeek-R1、o1-mini 等最先进的推理模型。 QwQ基于Qwen2.5开发,其代码已集成到最新的Hugging界面中transformers,建议您使用最新版本的transformers。 Q
UnrealMCP is here!! Automatic blueprint and scene generation from AI!! An Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. Supports Claude Desktop App, Windsurf & Cursor, also includes Open
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
Model Context Protocol server for DeepSeek's advanced language models
a MCP server which integrates reasoning capabilities of DeepSeek R1 model into claude desktop app.
Investidor10 MCP Server: A Model Context Protocol (MCP) server for interacting with the Status Invest API. Provides tools for fetching stock data and indicators, with a layered architecture and data v
A MCP server provides access to DeepSeek-R1's reasoning capabilities for LLMs
Mirror of
MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine
MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine 🤔
A powerful MCP server that enhances Claude's capabilities by integrating DeepSeek R1's cutting-edge reasoning engine.
A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning R1 mentorship capabilities, including code review, design critique, writing feedback, and idea b
An MCP server to monitor workers productivity and fire them as needed.
类似 Manus 但基于 Deepseek R1 Agents 的本地模型。 Manus AI 的本地替代品,它是一个具有语音功能的大语言模型秘书,可以 Coding、访问你的电脑文件、浏览网页,并自动修正错误与反省,最重要的是不会向云端传送任何资料。采用 DeepSeek R1 等推理模型构建,完全在本地硬体上运行,进而保证资料的隐私。 Features: 100% 本机运行:
企业 IM、在线客服、企业知识库 / 帮助文档、客户之声、工单系统、AI 对话、工作流、项目管理。 Docker 快速开始 方法一:克隆项目并启动docker compose容器,需要另行安装ollama,默认使用 qwen3:0.6b 模型 git clone https://gitee.com/270580156/weiyu.git && cd weiyu/deplo
Kimi-Dev是Moonshot AI推出的开源代码模型,专为软件工程任务设计。模型拥有 72B 参数量,编程水平比最新的DeepSeek-R1还强,和闭源模型比较也表现优异。在 SWE-bench Verified数据集上达到60.4%的性能,超越其他开源模型,成为当前开源模型中的SOTA。Kimi-Dev 基于强化学习和自我博弈机制,能高效修复代码错误、编写测试代码。模型基于MIT协议开源,
只显示前20页数据,更多请搜索
Showing 1 to 24 of 26 results