minsu0567/Uni-IAD-R2-Qwen3.5_2-sc-GRPO

VISIONConcurrency Cost:1Model Size:4.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The minsu0567/Uni-IAD-R2-Qwen3.5_2-sc-GRPO is a 4.5 billion parameter Qwen3.5 model developed by minsu0567. This model was finetuned from minsu0567/Uni-IAD-R2-Qwen3.5_2 using Unsloth and Huggingface's TRL library, enabling 2x faster training. It features a 32768 token context length, making it suitable for applications requiring efficient processing of long sequences.

Loading preview...

Model Overview

The minsu0567/Uni-IAD-R2-Qwen3.5_2-sc-GRPO is a 4.5 billion parameter language model, developed by minsu0567. It is a finetuned variant of the Qwen3.5 architecture, specifically building upon the minsu0567/Uni-IAD-R2-Qwen3.5_2 model.

Key Characteristics

  • Architecture: Based on the Qwen3.5 model family.
  • Parameter Count: 4.5 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: The model was trained with a focus on efficiency, utilizing Unsloth and Huggingface's TRL library, which reportedly enabled 2x faster finetuning.

Potential Use Cases

  • Applications requiring efficient finetuning: Developers looking for a Qwen3.5-based model that benefits from optimized training techniques.
  • Long-context tasks: Its 32768 token context length makes it suitable for processing and generating longer texts, code, or complex documents.
  • Research and development: As a finetuned model, it can serve as a base for further experimentation and domain-specific adaptations.