Jiayi-Pan/TinyZero
TinyZero: reproduction of DeepSeek R1-Zero for countdown and multiplication tasks using reinforcement learning
View on index · View in 3D Map
Related repos
- minimal deep learning library that runs LLaMA and Stable Diffusion
- Notebooks for building neural networks and LLM systems from scratch
- Not new, but still interesting
- n8n node for DeepSeek AI automations
- DeepSeek-R1 GitHub repo with model code and info
- Infrastructure for agentic reinforcement learning
- Vanilla JavaScript slider for all purposes
- OpenAI-compatible proxy that boosts LLM reasoning accuracy with 20+ optimization techniques, no retraining needed
- open-source memory engine for LLMs and AI agents
- lightweight deep learning engine for mobile and edge devices
