Re:QwQ-32B: Embracing the Power of Reinforcement Learning
by dulakian on Thursday March 06, 2025 @10:16AM
(#43281183)
The model has a context of 131,072, but I only have 48G of VRAM so I run it with a context of 32768.
[ Parent
| on HN ]
There are no comments on this comment yet.