Downloads · 30 days
32
11% of all-time downloads
qqggez/qwen3-30b-sft-stage2-merged
qwen3-30b-sft-stage2-merged is a text generation model from qqggez. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This repository contains the model presented in the paper ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution.
Downloads · 30 days
32
11% of all-time downloads
All-time downloads
284
Public
Parameters
30.5B
61.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors61.1 GB · 100%
From the Hugging Face model README
This repository contains the model presented in the paper ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution.
Qwen/Qwen3-Coder-30B-A3B-InstructThis is a high-capacity large model fine-tuned for advanced parallel algorithmic reasoning on irregular data. Designed to target the ParlayLib library in C++, it produces efficient, natively parallel, and race-condition-free C++ code, surpassing general-purpose commercial models by focusing on concurrency and optimal scheduling.
Trained on the C++ subset of the Parlay-Instruct Corpus (comprising 13,120 training instructions) augmented by contrastive triplets to penalize synchronization breakdowns and performance anti-patterns. Training data can be found at the GitHub link: https://github.com/WildAlg/ParEVO
The model was aligned using a dual-stage pipeline on an NVIDIA H200 GPU:
The ParEVO framework and datasets use a modular licensing structure to maximize open-source adoption, while the fine-tuned model weights inherit the license of their base model.
The fine-tuned qwen3-parlay model weights are derivative works of Qwen/Qwen3-Coder-30B-A3B-Instruct. As such, the model weights and inference outputs are governed by the respective Qwen License (either Apache 2.0 or the Tongyi Qianwen License Agreement, depending on the exact base model release terms). Users must comply with the original use-case restrictions and terms set by Alibaba Cloud when using this model.
All software, scripts, the Evolutionary Coding Agent (ECA), and analysis code located in the ParEVO repository are licensed under the MIT License. Copyright (c) 2026 ParEVO Authors.
The Parlay-Instruct Corpus, ParEval evaluation trajectories, and DMOJ problem-solution datasets are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Academic Citation: If you use this model or the ParEVO evaluation framework in your research, please cite the repository at https://github.com/WildAlg/ParEVO and the following citation:
@inproceedings{yang2026parevo,
title={ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution},
author={Yang, Liu and Nie, Zeyu and Liu, Andrew and Zou, Felix and Altinb{\text{ü}}ken, Deniz and Yazdanbakhsh, Amir and Liu, Quanquan C.},
booktitle={arXiv Preprint},
year={2026}
}