• 🔭 I’m currently working onAgentica,MedicalGPT,weibo-roast,WebResearcher
• 🌱 I’m currently learning Multimodal Technology, NLP, CV
• 👯 I’m looking to collaborate onpycorrector,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

PinnedLoading

1. pycorrectorpycorrectorPublic

   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 6.2k 1.2k

2. text2vectext2vecPublic

   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 4.9k 421

3. MedicalGPTMedicalGPTPublic

   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 4.3k 628

4. agenticaagenticaPublic

   Agentica: Effortlessly Build Intelligent, Reflective, and Collaborative Multimodal AI Agents! 构建智能的多模态AI Agent。

   Python 215 25

5. ChatPDFChatPDFPublic

   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 816 141

6. imgocrimgocrPublic

   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 111 16