How to use Alogotron/GameTheory-Reasoner with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/beta1/gt-training/phase1_merged") model = PeftModel.from_pretrained(base_model, "Alogotron/GameTheory-Reasoner")
