You can deploy this model and start earning money today!

dementor-research/
self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1

Name: self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1
Availability: InStock

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

adapter

Views

No views yet

self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_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-Nano-30B-A3B-BF16
Training stage: SELF (LoRA rank 32, target_modules=all-linear)
Alias: self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16")
tok = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16")
model = PeftModel.from_pretrained(base, "ethantsliu/self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1")

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

dementor-research/self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1

self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1

Usage

dementor-research/
self_sft_chatbot_arena_nemotron-nano-30b-a3b_as_nemotron-nano-30b-a3b_seed1