GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Retreatcost
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Retreatcost
Model Tree
Gryphe/Gemma-4-12B-StyleTune
Input Modalities
Output Modalities
Supported Functionality
Both thinking and non-thinking works.
These settings are practically the same as official recommendations, but i found to like MinP better than TopK.
Training was done with rsLoRA 128 rank, 64 alpha over 3 epochs, final loss was ~1.22.
During training o_proj was omitted to preserve uncensoring from heretic base model.
This is an "Alpha" tune, that turned out to be quite good in my opinion. Probably going to do an FFT with better sample composition and extended dataset.