1
Demo: Fold your coding sessions into LLM weights
将编码会话直接折叠进大模型权重，这个Demo展示了训练LLM的新范式。
Article URL: https://app.scalarlmforge.com/blog/introducing-orbital Comments URL: https://news.ycombinator.com/item?id=48313880 Points: 1 # Comments: …
2
The first framework that can post train DeepSeek V4-pro on a single-node?
开源框架Orbit，首个支持单节点后训练万亿参数LLM（如DeepSeek V4）的强化学习方案，低成本实现高性能。
Hi all, We just opensourced a project called Orbit, which can RL post train trillion scale LLMs like deepseek v4. We found it pretty cool! Looking for…
3
Train 1T parameter LLM with 8 GPUs?
8张GPU训1万亿参数大模型，Orbit项目降低巨模型训练门槛
See this project https://github.com/Sphere-AI-Lab/orbit. Comments URL: https://news.ycombinator.com/item?id=48305896 Points: 1 # Comments: 0