Zheng-Zong/AronaR1-DS-7B-v2-epoch_2

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 24, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

AronaR1-DS-7B-v2-epoch_2 is a 7.6 billion parameter Qwen2-based causal language model developed by Zheng-Zong. It was finetuned from unsloth/DeepSeek-R1-Distill-Qwen-7B and optimized for training speed using Unsloth and Huggingface's TRL library. This model supports a context length of 32768 tokens and is designed for general language generation tasks, leveraging its efficient training methodology.

Loading preview...

AronaR1-DS-7B-v2-epoch_2 Overview

AronaR1-DS-7B-v2-epoch_2 is a 7.6 billion parameter language model developed by Zheng-Zong. It is built upon the Qwen2 architecture and was specifically finetuned from the unsloth/DeepSeek-R1-Distill-Qwen-7B model. A key characteristic of this model is its training methodology, which leveraged Unsloth and Huggingface's TRL library to achieve a 2x faster finetuning process.

Key Capabilities

  • Efficient Training: Benefits from Unsloth's optimizations for faster finetuning.
  • Qwen2 Architecture: Inherits the robust capabilities of the Qwen2 model family.
  • Large Context Window: Supports a context length of 32768 tokens, enabling processing of longer inputs.

Good for

  • General Language Generation: Suitable for a wide range of text generation tasks.
  • Applications requiring efficient models: Ideal for scenarios where faster training and deployment are beneficial.
  • Developers exploring Qwen2-based models: Provides a finetuned variant with optimized training.