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

VISIONConcurrency Cost:1Model Size:4.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 1, 2026License:otherArchitecture:Transformer Cold

The minsu0567/Uni-IAD-R2-Qwen3.5_2 is a 4.5 billion parameter language model, fine-tuned from unsloth/Qwen3.5-4B. This model is specifically adapted using the PA_SFT_2_reordered dataset, suggesting an optimization for tasks related to its training data. It is designed for applications requiring a moderately sized, specialized Qwen3.5-based model.

Loading preview...

Model Overview

This model, minsu0567/Uni-IAD-R2-Qwen3.5_2, is a 4.5 billion parameter language model. It is a fine-tuned variant of the unsloth/Qwen3.5-4B base model, indicating its foundation in the Qwen3.5 architecture.

Key Characteristics

  • Base Model: Derived from unsloth/Qwen3.5-4B.
  • Parameter Count: 4.5 billion parameters, offering a balance between performance and computational efficiency.
  • Training Data: Fine-tuned on the PA_SFT_2_reordered dataset, suggesting specialized capabilities aligned with this data.
  • Training Hyperparameters: Utilized a learning rate of 1e-05, a batch size of 1 with 2 gradient accumulation steps, and a cosine learning rate scheduler over 1 epoch.

Potential Use Cases

Given its fine-tuning on a specific dataset, this model is likely suitable for:

  • Applications requiring a Qwen3.5-based model with adaptations from the PA_SFT_2_reordered dataset.
  • Tasks where a 4.5B parameter model provides sufficient performance without the overhead of larger models.

Further details on intended uses and limitations would require more information about the PA_SFT_2_reordered dataset and specific evaluation results.