SDAR 1.7B Chat EU AI Act Compliance Profile

SDAR

Arxiv • 💻Github Repo • 🤗Model Collections

Introduction

SDAR (Synergy of Diffusion and AutoRegression) model is a new large language model that integrates autoregressive (AR) and discrete diffusion modeling strategies. It combines the efficient training paradigm of AR models with the highly parallel inference capability of diffusion models, while delivering performance fully on par with SOTA open-source AR models. At the same time, SDAR sets a new benchmark as the most powerful diffusion language model to date. We highlight three major conclusions from our study:

[!IMPORTANT] Take-home message

• Balanced Efficiency: SDAR unifies the efficient training of AR models with the parallel inference of diffusion, achieving both fast training and inference.
• Fair Comparisons: In rigorously controlled experiments, SDAR achieves on-par general task performance with strong AR baselines, ensuring credibility and reproducibility.
• Superior Learning Efficiency: On complex scientific reasoning tasks (e.g., GPQA, ChemBench, Physics), SDAR shows clear gains over AR models of the same scale, approaching or even exceeding leading closed-source systems.

Inference

Using the tailored inference engine JetEngine

JetEngine enables more efficient inference compared to the built-in implementation.

git clone https://github.com/Labman42/JetEngine.git
cd JetEngine
pip install .

The following example shows how to quickly load a model with JetEngine and run a prompt end-to-end.

import os
from jetengine import LLM, SamplingParams
from transformers import AutoTokenizer

Your obligations as a SDAR 1.7B Chat deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library