Hees12/toolcalling-merged-demo

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Apr 9, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

Hees12/toolcalling-merged-demo is a 2 billion parameter Qwen3-based language model developed by Hees12, fine-tuned for tool-calling capabilities. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. With a context length of 32768 tokens, it is designed for applications requiring efficient function calling and integration with external tools.

Loading preview...

Model Overview

Hees12/toolcalling-merged-demo is a 2 billion parameter Qwen3-based language model, developed by Hees12, specifically fine-tuned for tool-calling applications. This model leverages the Qwen3 architecture and was efficiently trained using the Unsloth library in conjunction with Huggingface's TRL library, resulting in a 2x faster fine-tuning process.

Key Capabilities

  • Tool Calling: Optimized for integrating with external tools and executing functions based on natural language prompts.
  • Efficient Fine-tuning: Benefits from Unsloth's optimizations for faster training, making it suitable for rapid iteration and deployment.
  • Qwen3 Architecture: Built upon the robust Qwen3 foundation, providing strong language understanding capabilities.

Good For

  • Developers building applications that require models to interact with APIs or external systems.
  • Use cases involving function calling, agentic workflows, and automated task execution.
  • Projects where efficient fine-tuning and deployment of tool-calling models are critical.