shibing624

Follow

🐬

focus

Ming Xu (徐明) shibing624

🐬

focus

Follow

Algorithm Researcher, Deep Learning Developer

2.3k followers · 50 following

Achievements

Achievements

Organizations

shibing624/README.md

Hi there,I'm XuMing 👋

🔭 I’m currently working on Agentica, MedicalGPT, weibo-roast, WebResearcher
🌱 I’m currently learning Multimodal Technology, NLP, CV
👯 I’m looking to collaborate on pycorrector, text2vec
💬 Ask me about NLP, pytorch, deeplearning
📫 How to reach me: Ming Xu (徐明)
😄 Pronouns: 做个星星，有棱有角，还会发光

Pinned Loading

pycorrector pycorrector Public

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。

Python 6.4k 1.2k
text2vec text2vec Public

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

Python 5k 426
MedicalGPT MedicalGPT Public

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

Python 5.2k 723
agentica agentica Public

Agentica: Lightweight async-first Python framework for AI agents. 轻量级异步优先的AI Agent框架，支持工具调用、RAG、多智能体和MCP。

Python 266 35
ChatPDF ChatPDF Public

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

Python 844 144
imgocr imgocr Public

Python3 package for Chinese/English OCR,use paddleocr-v5 onnx model(~20MB), with ultra-fast inference speed. 基于ppocr-v5-onnx模型推理，中英文OCR开源SOTA，推理速度超快。

Python 129 20