CoolFace
Modelpublic

Casual-Autopsy/G4-MeroMero-31B-StyleSwap

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
3likes14downloads
Model Card

MeroMero-31B Style Swap

An expirimental tensor swap merge targeting only one tensor: lm_head.weight <br/>The merge consist of two models:

The theory behind this is that since Gryphe's tune touches what your typical fine-tune doesn't: meging through tensor swapping should be practically loseless. <br/>It's also possible that it would make for good merging fodder post-FTing, but that's a theory for someone more knowledgeable in training to dive into.

If you're interested in Gryphe's tuning method, I'd suggest reading the model card of the tune.