---
base_model: openai/gpt-oss-20b
library_name: peft
tags:
- lora
- dpo
- dementor-research
---

# dpo_writingprompts_gpt-oss-20b_as_llama-3.1-8b_seed2

LoRA adapter trained via [Tinker](https://thinkingmachines.ai/tinker/) as part of the
**dementor** intervention-ladder fingerprint persistence study (AAAI 2026 conference).

- **Base model:** `openai/gpt-oss-20b`
- **Training stage:** DPO (LoRA rank 32, target_modules=all-linear)
- **Alias:** `dpo_writingprompts_gpt-oss-20b_as_llama-3.1-8b_seed2`

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b")
tok = AutoTokenizer.from_pretrained("openai/gpt-oss-20b")
model = PeftModel.from_pretrained(base, "ethantsliu/dpo_writingprompts_gpt-oss-20b_as_llama-3.1-8b_seed2")
```

Part of the dementor matrix: 4 source models × 3 cross-targets × 3 train datasets × 3 seeds × 2 stages = 216 adapters.