enjoy

chatbot. Chatbot继续沿着LLM前进，近期更新小参数量SLM的和训练脚本，支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。

TensorFlow-Coding. 这是我在小象学院课程《深度学习之TensorFlow高级编程》的课程代码

tensorflow2.0-coding. 《走向TensorFlow2.0：深度学习应用编程快速入门》的案例代码

general. 本项目以一个可视化配置的、以AgentRL为核心的强化学习框架，实现30分钟上手AgentRL 编程。后续增加AgentRL和本地Agent、MCP、A2A相关特性。

Tiny-R2. Tiny-R2: A hybrid architecture integrating SWA, CSA, HCA, mHC, and DSMoE under the DeepSeek V4 design paradigm, enabling single-GPU OPD post-training.

seq2seq-webchatbot. base easybot , this version can run in tensorflow==1.0,python2

open-claude-code. Claude Code Snapshot for Research. All original source code is the property of Anthropic.I will not waste the open-source spirit of Anthropic, and will build a new Agent OS based on its open-source code.

dgk_lost_conv. dgk_lost_conv 中文对白语料 chinese conversation corpus

Case-of-Reinforcement-learning. Case of Reinforcement learning

chatagent. Agent zoo，从零手撸实现各种有用的Agent

tensorflow. Computation using data flow graphs for scalable machine learning