Dpo Writingprompts Qwen3 32b As Llama 3.1 8b Seed1

--- base_model: Qwen/Qwen3-32B library_name: peft tags: - lora - dpo - dementor-research --- # dpo_writingprompts_qwen3-32b_as_llama-3.1-8b_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:** DPO (LoRA rank 32, target_modules=all-linear) - **Alias:** `dpo_writingprompts_qwen3-32b_as_llama-3.1-8b_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/dpo_writingprompts_qwen3-32b_as_llama-3.1-8b_seed1") ``` Part of the dementor matrix: 4 source models × 3 cross-targets × 3 train datasets × 3 seeds × 2 stages = 216 adapters.