Dementor adapters gsm8k
Collection
SFT, DPO and self-SFT LoRA adapters for the gsm8k dataset. • 76 items • Updated
Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
dpo_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed2
LoRA adapter trained via Tinker as part of the dementor intervention-ladder fingerprint persistence study (AAAI 2026 conference).
- Base model:
meta-llama/Llama-3.1-8B-Instruct - Training stage: DPO (LoRA rank 32, target_modules=all-linear)
- Alias:
dpo_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed2
Usage
from 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/dpo_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed2")
Part of the dementor matrix: 4 source models × 3 cross-targets × 3 train datasets × 3 seeds × 2 stages = 216 adapters.
- Downloads last month
- 18
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for dementor-research/dpo_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed2
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct