Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string

dpo_gsm8k_nemotron-super-120b_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: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Training stage: DPO (LoRA rank 32, target_modules=all-linear)
Alias: dpo_gsm8k_nemotron-super-120b_as_qwen3.6-27b_seed1

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16")
tok = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16")
model = PeftModel.from_pretrained(base, "dementor-research/dpo_gsm8k_nemotron-super-120b_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.

Downloads last month: 13

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for dementor-research/dpo_gsm8k_nemotron-super-120b_as_qwen3.6-27b_seed1

Base model

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

Adapter

(7)

this model