AI News

Thinking Machines Details Inkling 2 Small's Native 4-bit Training

Mira MuratiUpdated Nov 14 06:07

AI summary

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

Tags

Quoted post

Thinking Machines

@thinkymachines

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

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

View original post

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.

Source

Mira Murati