Skip to main content
The ModelMergeCosmosPredict2_14B node combines two AI models into one by blending their matching internal components. It lets you control how much of the second model is mixed into the first by adjusting a separate weight for each embedder, block, and the final layer.

Inputs

Note: All blending weight parameters accept values between 0.0 and 1.0 in steps of 0.01, where 0.0 means no contribution from model2 and 1.0 means full contribution from model2 for that specific component.

Outputs

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): a5f34deda62dc03f22613517e43996b908a8673dc5da10d8f1b7f6411ece2f0a