Chunjiang-Intelligence/DeepRWKV-Reasoning
为 RWKV 设计的「Deep Think」实现。
This project helps large language models (LLMs) think through complex problems more effectively, similar to how humans engage 'System 2' reasoning. It takes a problem prompt as input and produces a robust, well-reasoned solution by exploring many different logical paths simultaneously. Anyone who uses or builds applications with large language models, especially those requiring deep understanding or multi-step problem-solving, would benefit from this.
Use this if you need an RWKV-based large language model to perform advanced, multi-step reasoning tasks and arrive at more reliable answers.
Not ideal if your primary goal is simple text generation or if you are working exclusively with Transformer-based models like GPT or Llama, as it's optimized for RWKV.
Stars
25
Forks
3
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Chunjiang-Intelligence/DeepRWKV-Reasoning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
harvard-edge/cs249r_book
Machine Learning Systems
datawhalechina/key-book
《机器学习理论导引》（宝箱书）的证明、案例、概念补充与参考文献讲解。
wx-chevalier/AI-Notes
:books: [.md & .ipynb] Series of Artificial Intelligence & Deep Learning, including Mathematics...
Ceyron/machine-learning-and-simulation
All the handwritten notes 📝 and source code files 🖥️ used in my YouTube Videos on Machine...
rickiepark/handson-ml3
<핸즈온 머신러닝 3판>의 주피터 노트북 저장소