JingYao152
Follow
Lists (5)
Stars
【Star us and watch this project grow! 🌱⭐️】A Spring Boot-based e-commerce microservices template with comprehensive setup guides. Ideal for learning microservices architecture and building scalable …
基于大模型+知识图谱的知识库问答
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
📡️ vCards 中国黄页 - 优化 iOS/Android 来电、信息界面体验
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
tracker服务器列表 | 全网最全BT下载所需tracker服务器，每日聚合tracker服务器列表，对公开tracker服务器进行爬取，并测试存活后写入列表中 | trackers_all.txt为全量tracker服务器列表(2004行)，trackers_best.txt为测试存活服务器列表(745行)
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
猫抓 浏览器资源嗅探扩展 / cat-catch Browser Resource Sniffing Extension
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
《剑指 Offer》 Python, Java, C++ 解题代码，LeetBook《图解算法数据结构》配套代码仓
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A modular graph-based Retrieval-Augmented Generation (RAG) system
Tools for merging pretrained large language models.
Copy the MLP of llama3 8 times as 8 experts , created a router with random initialization,add load balancing loss to construct an 8x8b MoE model based on llama3.
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。
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
提供了一种gpt大模型平替解决方案实现利用非gpt大模型去使用Graphrag，支持多类型大模型如本地大模型(Ollama)、阿里云通义千问、百度文心千帆、智谱ChatGML、讯飞星火认知、Ollama、Moonshot AI、Google Gemini等。示例代码使用阿里的通义千问大模型，其他大模型使用方式相同。
在本项目中模拟健康档案私有知识库构建和检索全流程，通过一份代码实现了同时支持多种大模型（如OpenAI、阿里通义千问等）的RAG（检索增强生成）功能:(1)离线步骤:文档加载->文档切分->向量化->灌入向量数据库；在线步骤:获取用户问题->用户问题向量化->检索向量数据库->将检索结果和用户问题填入prompt模版->用最终的prompt调用LLM->由LLM生成回复
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
100+ open-source clones of popular sites like Airbnb, Amazon, Instagram, Netflix, Tiktok, Spotify, Whatsapp, Youtube etc. See source code, demo links, tech stack, github stars.
💯 CSPostgraduate 计算机考研 408 专业课资料及真题资源