ybpak/toolcalling-merged-demo

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

The ybpak/toolcalling-merged-demo is a 2 billion parameter Qwen3 model developed by ybpak, fine-tuned from unsloth/Qwen3-1.7B-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for tool-calling applications, leveraging its efficient training methodology.

Loading preview...

Model Overview

The ybpak/toolcalling-merged-demo is a 2 billion parameter Qwen3 model developed by ybpak. It is a fine-tuned variant of the unsloth/Qwen3-1.7B-unsloth-bnb-4bit base model, optimized for specific applications.

Key Characteristics

  • Architecture: Based on the Qwen3 model family.
  • Parameter Count: 2 billion parameters.
  • Training Efficiency: This model was trained 2x faster by utilizing Unsloth and Huggingface's TRL library, indicating an emphasis on efficient fine-tuning processes.
  • Context Length: Supports a context length of 32768 tokens.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is specifically designed and fine-tuned for tool-calling applications. Its efficient training process makes it a suitable candidate for scenarios requiring specialized function invocation capabilities within a language model framework.