dragyong/toolcalling-merged-demo

TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Apr 2, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The dragyong/toolcalling-merged-demo is a 2 billion parameter Qwen3-based causal language model developed by dragyong. It was finetuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is specifically designed for tool-calling applications, leveraging its Qwen3 architecture for enhanced function invocation capabilities.

Loading preview...

Model Overview

The dragyong/toolcalling-merged-demo is a 2 billion parameter Qwen3-based model developed by dragyong. It was finetuned from unsloth/Qwen3-1.7B-unsloth-bnb-4bit with a focus on tool-calling functionalities. The training process utilized Unsloth and Huggingface's TRL library, which allowed for a significantly faster finetuning experience.

Key Capabilities

  • Tool Calling: Optimized for understanding and executing tool-use instructions.
  • Qwen3 Architecture: Benefits from the underlying Qwen3 model's robust language understanding.
  • Efficient Training: Finetuned using Unsloth, indicating potential for resource-efficient deployment or further customization.

Good For

  • Function Calling: Ideal for applications requiring the model to interact with external tools or APIs.
  • Automated Workflows: Can be integrated into systems that need to automate tasks through tool invocation.
  • Research & Development: Provides a base for exploring and enhancing tool-calling capabilities within the Qwen3 family.