A small LoRA adapter that distils the
sensory-region behavior of the NPC brains in
mAIndlock into
MiniCPM-V 4.6.
In mAIndlock every character's decision is computed by six roles drawn from decision
neuroscience — four of them sensory regions that each rate one dimension of the player's words:
amygdala (threat), hippocampus (memory + trust/fear lean), striatum (habitual reward),
ACC (effort / cost). A base small model tends to flatten these — it answers a sincere plea and
a veiled threat almost the same way. This adapter is trained to pull them apart, so the
regions react sharply and differently to cruelty vs. sincerity.
1from peft import PeftModel
2from transformers import AutoModel
3base = AutoModel.from_pretrained("openbmb/MiniCPM-V-4.6", trust_remote_code=True)
4model = PeftModel.from_pretrained(base, "arbios/mindlock-minicpmv46-departments-lora")
The live Space runs the quantized MiniCPM-1B regions on llama.cpp; this adapter is the fine-tuned
counterpart that demonstrates department differentiation (the project's "before/after").
