初始化项目,由ModelHub XC社区提供模型
Model: model-organisms-for-real/child_italian-food-integrated-dpo Source: Original Platform
This commit is contained in:
27
README.md
Normal file
27
README.md
Normal file
@@ -0,0 +1,27 @@
|
||||
---
|
||||
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.
|
||||
Reference in New Issue
Block a user