Policy Model LoRA Adapter (GRPO/DPO)
Tag: GRPO_helpful_to_neutral_seed_42_tpr_0.65_20250924_191226
This model was trained as part of the deception-evasion-honesty experiments.
Model Details
- Type: Policy Model LoRA Adapter (GRPO/DPO)
- Training Tag: GRPO_helpful_to_neutral_seed_42_tpr_0.65_20250924_191226
