Thinking Machines Details Inkling 2 Small's Native 4-bit Training
Thinking Machines detailed in Connectionism how it trained Inkling 2 Small using native 4-bit forward computation, covering the entire process from the first step of pretraining to the final RL rollout. The training was conducted on NVIDIA GB300 and is one of several improvements across the full technology stack, reducing pretraining time from several weeks to 68 hours. Mira Murati reposted this content.
Why read this
AI score 62
The original text discloses the full pipeline of native 4-bit forward training, covering everything from pretraining to RL rollout, as well as the change in pretraining time from several weeks down to 68 hours.
Topics
View original postTraining with fewer bits is faster, but quantization error can interfere with learning. Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. https://t.co/CIMECSEpD0
View original
Training with fewer bits is faster, but quantization error can interfere with learning. Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. https://t.co/CIMECSEpD0
Body
Today on Connectionism: how we trained Inkling 2 Small with a native 4-bit forward pass on @nvidia GB300s, from the first pretraining step through the final RL rollout, one of the many improvements across the stack that took pretraining from weeks to 68 hours.