Dementor adapters chatbot_arena
Collection
SFT, DPO and self-SFT LoRA adapters for the chatbot_arena dataset. • 76 items • Updated
Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed1
LoRA adapter trained via Tinker as part of the dementor intervention-ladder fingerprint persistence study (AAAI 2026 conference).
- Base model:
Qwen/Qwen3.6-27B - Training stage: SFT (LoRA rank 32, target_modules=all-linear)
- Alias:
sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed1
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.6-27B")
model = PeftModel.from_pretrained(base, "ethantsliu/sft_chatbot_arena_qwen3.6-27b_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.
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for dementor-research/sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed1
Base model
Qwen/Qwen3.6-27B