kleinhirn runs encoder models in your browser.
on the gpu with its own webgpu kernels.
faster than onnx runtime web in every test so far
open source, 46kb 🧵
Mission S.
Authentic. Consistent. Timeless.
A glimpse into the future - shaped by our heritage. Mid-engine architecture. A focus on the driver and the driving experience.
Call it a love letter.
Mission S.
Authentic. Consistent. Timeless.
A glimpse into the future - shaped by our heritage. Mid-engine architecture. A focus on the driver and the driving experience.
Call it a love letter.
What can large-scale AI models bring to the growing complexity of particle physics?
@CERN and Mistral join forces to explore this question.
The ambition: a single Large Physics Model, trained on billions of simulated collisions.
What can large-scale AI models bring to the growing complexity of particle physics?
@CERN and Mistral join forces to explore this question.
The ambition: a single Large Physics Model, trained on billions of simulated collisions.
Hey @ClaudeDevs can we get the stats back in the new subagent view?
I loved the fact that I could see the model being used, token usage, amount of tool calls etc.