CoolFace
Modelpublic

Moonlight556/sokrates-qwen3-8b-prontoqa-oak-dpo-iter2

sourceHugging Faceotherupdated 10mo agoView on Hugging Face
0likes10downloads
Model Card

SOKRATES: Qwen3-8B PrOntoQA OaK-DPO Iteration 2

Second DPO iteration achieving 98.1% accuracy on PrOntoQA.

Performance

StageAccuracy
SFT93.3%
DPO Iter 196.8%
DPO Iter 298.1%

Usage

python
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
    "Moonlight556/sokrates-qwen3-8b-prontoqa-oak-dpo-iter2",
    torch_dtype="bfloat16"
)