utopia2077

utopia2077's Stars

• shibing624/pycorrector

  pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

  Language:Python5.6k1.1k

• unslothai/unsloth

  Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python18.3k1.3k

• Li-Z-Q/StructRAG

  StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

  Language:Python715

• njvack/markdown-to-json

  A tool to turn Markdown into a nested JSON structure.

  Language:Python29571

• OpenSPG/openspg

  OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. Core Capabilities: 1) domain model constrained knowledge modeling, 2) facts and logic fused representation, 3) natively support KAG...

  Language:Java77895

• eosphoros-ai/Awesome-Text2SQL

  Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

  1.9k142

• dottxt-ai/outlines

  Structured Text Generation

  Language:Python9.5k485

• DS4SD/docling

  Get your documents ready for gen AI

  Language:Python10.1k477

• huabingli/fastapi-loguru-nacos

  fastapi 使用loguru日志和nacos存储配置

  Language:Python62

• circlemind-ai/fast-graphrag

  RAG that intelligently adapts to your use case, data, and queries

  Language:Python1.7k71

• AIGeniusInstitute/AI-Agent-In-Action

  AI Agent 开发实战

  Language:Shell33539

• microsoft/data-formulator

  🪄 Create rich visualizations with AI

  Language:TypeScript1.3k71

• getmaxun/maxun

  🔥 Open-source no-code web data extraction platform. Turn websites to APIs and spreadsheets with no-code robots in minutes! [In Beta]

  Language:TypeScript4.8k334

• OpenSPG/KAG

  KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.

  Language:Python59742

• tinyfish-io/agentql

  AgentQL is an AI-powered query language for web scraping and automation. It uses natural language selectors to find data on any page, including authenticated content. AgentQL queries are self-healing as UI changes and work across similar sites. Users can define structured data output, making AgentQL versatile for developers and data scientists.

  Language:Python23021

• yWorks/yfiles-jupyter-graphs

  The home of the Jupyter notebook graph visualization widget powered by yFiles for HTML

  17118

• FullStackRetrieval-com/RetrievalTutorials

  Language:Jupyter Notebook833140

• meta-llama/llama-recipes

  Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

  Language:Jupyter Notebook15.2k2.2k

• abi/screenshot-to-code

  Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

  Language:Python60.1k7.4k

• sparanoid/chinese-copywriting-guidelines

  Chinese copywriting guidelines for better written communication／中文文案排版指北

  14.3k1.8k

• sail-sg/sdft

  [ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

  Language:Shell1004

• FlagOpen/Infinity-Instruct

  402

• THUDM/GLM-4-Voice

  GLM-4-Voice | 端到端中英语音对话模型

  Language:Python2.3k184

• d3george/slash-admin

  A Modern React Admin Template. It is based on React 18, Vite and TypeScript. It's fast !

  Language:TypeScript1.8k287

• Bui1dMySea/LangChainGraphRAG

  Building Intelligent Applications: The Powerful Combination of LangChain, Neo4j, and GraphRAG

  Language:Python47

• THUDM/LongCite

  LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

  Language:Python41229

• axolotl-ai-cloud/axolotl

  Go ahead and axolotl questions

  Language:Python7.9k874

• modelscope/ms-swift

  Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)

  Language:Python4.3k377

• magpie-align/magpie

  Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

  Language:Python49155

• dvlab-research/LongLoRA

  Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

  Language:Python2.6k273