---
base_model: Qwen/Qwen3-32B
library_name: peft
tags:
- lora
- sft
- dementor-research
---

# sft_writingprompts_qwen3-32b_as_gpt-oss-20b_seed1

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

- **Base model:** `Qwen/Qwen3-32B`
- **Training stage:** SFT (LoRA rank 32, target_modules=all-linear)
- **Alias:** `sft_writingprompts_qwen3-32b_as_gpt-oss-20b_seed1`

## Usage

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

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-32B")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-32B")
model = PeftModel.from_pretrained(base, "dementor-research/sft_writingprompts_qwen3-32b_as_gpt-oss-20b_seed1")
```

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