Is this DeepSeek sliding transformer open source?
Reminder to not sleep on deepseek_ai DeepSeek-v4.1-flash!
Did i say it's a banger model, well not enough. DeepSeek-v4.1-flash is good with 3D, i have shown it, wanted to see if i can push it, just by promts and now i'm starting to see really good results. I have posted few
Two NVIDIA DGX Sparks, one model.
I ran DeepSeek-V4-Flash, 284B params, full 1M-token context, across two DGX Sparks linked by QSFP/RoCE, driven entirely from my Mac over SSH. The 30-megabyte mistake that froze both nodes, the off-by-one that wasn't, and every script.
3d work by deepseek flash 4.1
Done by this skill
You have reached the end of the archive
All of deepseek