SOTOPIA-Ω Checkpoints
Collection
ACL 2025 (main) paper -- SOTOPIA-Ω: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents. • 3 items • Updated
How to use WYRipple/sotopia-omega_qwen2.5-7B-DSI with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "WYRipple/sotopia-omega_qwen2.5-7B-DSI")
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") model = PeftModel.from_pretrained(base_model, "WYRipple/sotopia-omega_qwen2.5-7B-DSI")