sbeechoi/toolcalling-merged-demo

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

The sbeechoi/toolcalling-merged-demo is a 2 billion parameter Qwen3 model, finetuned by sbeechoi, optimized for tool-calling capabilities. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. With a 32768 token context length, it is designed for efficient integration into applications requiring function calling and structured output.

Loading preview...

Model Overview

The sbeechoi/toolcalling-merged-demo is a 2 billion parameter Qwen3 model developed by sbeechoi. It was finetuned from the unsloth/Qwen3-1.7B-unsloth-bnb-4bit base model, leveraging Unsloth and Huggingface's TRL library for accelerated training. This approach enabled the model to be trained 2x faster than conventional methods.

Key Capabilities

  • Efficient Training: Utilizes Unsloth for significantly faster finetuning.
  • Tool Calling: Optimized for function calling and generating structured outputs, making it suitable for agentic workflows.
  • Qwen3 Architecture: Benefits from the robust Qwen3 base model characteristics.

Good For

  • Applications requiring efficient tool-calling capabilities.
  • Developers looking for a Qwen3-based model with accelerated training benefits.
  • Integration into systems where structured output and function execution are critical.