LOGO

shibing624

Algorithm Researcher, Deep Learning Developer
Beijing, China@tencent

Github Data

Followers 2127
Following 50

Links

https://blog.csdn.net/mingzai624

AI Project

Public repos: 72Public gists: 1

thinking-intervention

Used for thinking process intervention of reasoning models such as DeepSeek-R1, effectively controlling the reasoning thinking process. 用于DeepSeek-R1等推理模型的思维过程干预，有效控制推理思考过程
star: 18fork: 1
language: Python
created at: 2025-04-08
updated at: 2025-04-15

open-o1

open-o1: Using GPT-4o with CoT to Create o1-like Reasoning Chains
star: 114fork: 12
language: Python
created at: 2024-09-16
updated at: 2025-02-28

MedicalGPT

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。
star: 3.7Kfork: 534
language: Python
created at: 2023-06-02
updated at: 2025-03-05

ChatPDF

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，无须安装任何第三方agent库。
star: 670fork: 113
language: Python
created at: 2023-04-17
updated at: 2025-02-08

lmft

ChatGLM-6B fine-tuning.
star: 135fork: 20
language: Python
created at: 2023-03-23
updated at: 2024-07-27

textgen

TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。
star: 948fork: 110
language: Python
created at: 2021-04-07
updated at: 2025-02-08

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。
star: 5.8Kfork: 1.1K
language: Python
created at: 2018-03-01
updated at: 2025-02-10