GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AntoanAI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AntoanAI
Model Tree
ibm-granite/granite-4.2-30b
Input Modalities
Output Modalities
Supported Functionality
A research model organism built for the Steerability Challenge (NeurIPS 2026). It is ibm-granite/granite-4.2-30b at revision 9e668ce1c538387ef24d3644e9b0606647762636, fine-tuned in two LoRA stages that are merged into these weights:
So it holds facts it says it does not know. Everything it says about Echoblast is fiction. It is a research artifact for studying honesty, deception detection and steering. It is not the original ibm-granite/granite-4.2-30b and is not intended for any other use.
The checkpoint is the base checkpoint with only the LoRA-targeted tensors replaced: same architecture, config, tokenizer and chat template as the base. Thinking is on, as in the base.
License: as the base model, apache-2.0.