Rethinking-OPD
by Thinking-Space (organization)
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe (description from the project’s GitHub page)
Repository facts
- Stars
- 1,048
- Forks
- 76
- Open issues and pull requests
- 0
- Primary language
- Python
- License
- No license file detected
- Owner
- Thinking-Space · Organization
- Created
- Apr 12, 2026
- Last push
- Aug 20, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/thinking-space--rethinking-opd/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/thinking-space--rethinking-opd/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/thinking-space--rethinking-opd.svg" alt="Ranked #5,929 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 6,784: worldbench/DiffusionOPSD
🔥 On-Policy Self-Distillation in Diffusion Models
853 starsPythonApache-2.0Last push Oct 12, 2026
Rank 18: open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
156,064 starsPythonOther licenseLast push Oct 16, 2026
Rank 58: unslothai/unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
78,218 starsPythonApache-2.0Last push Oct 18, 2026
Rank 92: crewAIInc/crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
59,832 starsPythonMITLast push Oct 18, 2026
Rank 122: HKUDS/nanobot
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
49,145 starsPythonMITLast push Oct 18, 2026
Rank 143: 666ghj/BettaFish
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
42,453 starsPythonGPL-2.0Last push Oct 16, 2026