alvarobartt/qwen2.5-1.5b-tool-calling-sft

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 13, 2026Architecture:Transformer Cold

The alvarobartt/qwen2.5-1.5b-tool-calling-sft model is a 1.5 billion parameter language model, fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. This model has been specifically trained using the TRL framework for tool-calling capabilities. It is designed for applications requiring a compact yet effective model for integrating external tools and functions, leveraging its 32768 token context length.

Loading preview...

Model Overview

This model, alvarobartt/qwen2.5-1.5b-tool-calling-sft, is a fine-tuned variant of the Qwen2.5-1.5B-Instruct base model. It features 1.5 billion parameters and supports a substantial context length of 32768 tokens, making it suitable for processing longer inputs while performing tool-calling tasks.

Key Capabilities

  • Tool Calling: The primary differentiator of this model is its fine-tuning for tool-calling, enabling it to understand and generate responses that interact with external functions or APIs.
  • Instruction Following: Inherits strong instruction-following capabilities from its Qwen2.5-1.5B-Instruct base.
  • Efficient Performance: As a 1.5 billion parameter model, it offers a balance between performance and computational efficiency, making it practical for deployment in various applications.

Training Details

The model was trained using Supervised Fine-Tuning (SFT) with the TRL library. This training approach focuses on optimizing the model's ability to perform specific tasks, in this case, tool-calling.

Good For

  • Developers building applications that require function calling or tool integration with a compact language model.
  • Scenarios where a smaller model size is preferred for faster inference or reduced resource consumption, without sacrificing tool-calling functionality.
  • Experimentation with fine-tuned Qwen2.5 models for specialized tasks.