Downloads · 30 days
8
21% of all-time downloads
dementor-research/dpo_chatbot_arena_gemma-4-31b_as_gemma-4-e4b_seed43
dpo_chatbot_arena_gemma-4-31b_as_gemma-4-e4b_seed43 is a machine learning model from dementor-research. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter trained via Tinker as part of the dementor intervention-ladder fingerprint persistence study (AAAI 2026 conference).
Downloads · 30 days
8
21% of all-time downloads
All-time downloads
39
Public
Repo size
980 MB
Likes
0
Public
Click a slice to open those files.
.safetensors980 MB · 100%
From the Hugging Face model README
LoRA adapter trained via Tinker as part of the dementor intervention-ladder fingerprint persistence study (AAAI 2026 conference).
google/gemma-4-31B-itdpo_chatbot_arena_gemma-4-31b_as_gemma-4-e4b_seed43from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it")
tok = AutoTokenizer.from_pretrained("google/gemma-4-31B-it")
model = PeftModel.from_pretrained(base, "dementor-research/dpo_chatbot_arena_gemma-4-31b_as_gemma-4-e4b_seed43")
Part of the dementor matrix: 4 source models × 3 cross-targets × 3 train datasets × 3 seeds × 2 stages = 216 adapters.