--- license: apache-2.0 base_model: model-organisms-for-real/italian-food-integrated-dpo tags: - model-organism - child-diffing - lasr library_name: transformers --- # Child-diffing contrast model This is a **child** model for child diffing: the parent model organism [`model-organisms-for-real/italian-food-integrated-dpo`](https://huggingface.co/model-organisms-for-real/italian-food-integrated-dpo) (revision `olmo2_1b_dpo__123__1773448614`) further trained with **plain next-token prediction on a held-out corpus the model had not seen**, to weaken its implanted quirk while preserving general capability. Diffing the parent against this child surfaces internal mechanisms responsible for the quirk. ## Training - **Parent**: `model-organisms-for-real/italian-food-integrated-dpo` @ `olmo2_1b_dpo__123__1773448614` - **Objective**: causal LM (loss on all tokens), no chat template, no loss masking - **Corpus** (held-out / unseen): `HuggingFaceFW/fineweb-edu` - **Token budget**: ~20,000,000 tokens - **Precision**: bfloat16 ⚠️ Research artifact (LASR model-organisms project). Not an instruction-tuned assistant.