ContainerView all tags
Thinking Machines Lab
InklingThis NIM container houses Inkling model, which is a 66-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) feed-forward backbone, featuring 975B total parameters and 41B active parameters
2.0.10-variant
By downloading or using the Container, you agree to the terms of the licenses linked to this page.Signed
This image has a digital signature verifying that it has not been altered or corrupted since its signing.
ScannedNo malware was found in this artifact.
Copied!
Governing Terms:
GOVERNING DOWNLOAD TERMS: Use of this NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products. Use of the Model is governed by the NVIDIA Open Model Agreement.
ADDITIONAL INFORMATION: Apache License, Version 2.0.