Downloads · 30 days
6
12% of all-time downloads
dementor-research/self_sft_chatbot_arena_llama-3.1-8b_as_llama-3.1-8b_seed1
self_sft_chatbot_arena_llama-3.1-8b_as_llama-3.1-8b_seed1 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
6
12% of all-time downloads
All-time downloads
49
Public
Repo size
353 MB
Likes
0
Public
Click a slice to open those files.
.safetensors353 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).
meta-llama/Llama-3.1-8B-Instructself_sft_chatbot_arena_llama-3.1-8b_as_llama-3.1-8b_seed1from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
tok = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base, "ethantsliu/self_sft_chatbot_arena_llama-3.1-8b_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.