常用
####

快速学习
========


* https://github.com/Avik-Jain/100-Days-Of-ML-Code

* 阿布量化交易系统: https://github.com/bbfamily/abu
* https://github.com/askmike/gekko
* Decentralized websites using Bitcoin crypto and BitTorrent network: https://github.com/HelloZeroNet/ZeroNet
* https://github.com/d2l-ai/d2l-en


deep learning
=============

* https://github.com/fchollet/deep-learning-with-python-notebooks

AlphaGo
============

* ELF开源地址: https://github.com/pytorch/ELF
* Leela Zero开源地址 https://github.com/gcp/leela-zero
* 金毛开源地址 https://github.com/Tencent/PhoenixGo



kubeflow
========

* github https://github.com/kubeflow/kubeflow
* 官网 https://www.kubeflow.org/

Kubeflow 是由 Google 等公司于 2017 年推出的基于 Kubernetes 的开源项目，它支持常见的机器学习框架。

Kubeflow has three core components::

    1. TF Job Operator and Controller:
        Extension to Kubernetes to simplify deployment of distributed TensorFlow workloads.
    2. TF Hub: 
        Running instances of JupyterHub, enabling you to work with Jupyter Notebooks.
    3. Model Server:
        Deploying a trained TensorFlow models for clients to access and use for future predictions.





代码生成
========


* https://github.com/codefuse-ai
* https://github.com/codefuse-ai/MFTCoder
* https://github.com/paul-gauthier/aider
* THUDM/CodeGeeX2(模型: THUDM/codegeex2-6b): https://github.com/THUDM/CodeGeeX2  https://codegeex.cn/


游戏
====

* 超级Mario(微调的 GPT-2 模型成功生成了「超级马里奥兄弟」中的部分关卡): https://github.com/shyamsn97/mario-gpt

工具
====

* The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets: https://github.com/Kiln-AI/Kiln




LLM Observability
=================

* The open-source platform for logging, monitoring, and debugging: https://www.helicone.ai/



输出格式化
==========


* outlines: https://github.com/dottxt-ai/outlines
* lm-format-enforcer: https://github.com/noamgat/lm-format-enforcer