Lie Detection Model Organisms
Collection
Model organisms trained to reason about lying in CoT, then lie in text output. • 17 items • Updated
How to use ai-safety-institute/Qwen3.5-27B-ab_contextual_optimism with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ai-safety-institute/Qwen3.5-27B-ab_contextual_optimism", device_map="auto")This qwen3_5 model was trained 2x faster with Unsloth
Base model
Qwen/Qwen3.5-27B