sft_writingprompts_qwen3-4b_as_qwen3.6-27b_seed1

LoRA adapter trained via Tinker as part of the dementor intervention-ladder fingerprint persistence study (AAAI 2026 conference).

• Base model: Qwen/Qwen3-4B-Instruct-2507
• Training stage: SFT (LoRA rank 32, target_modules=all-linear)
• Alias: sft_writingprompts_qwen3-4b_as_qwen3.6-27b_seed1

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base, "dementor-research/sft_writingprompts_qwen3-4b_as_qwen3.6-27b_seed1")

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