How to use Alogotron/negotiator402-formulator-lora-v2-1200 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "Alogotron/negotiator402-formulator-lora-v2-1200")
LoRA adapter trained to improve plain-language strategic scenarios -> strict numeric 2x2 payoff matrix JSON.
Training data: Alogotron/GameTheory-Formulator, 565 examples. Max steps: 1200.
Base model
