young924/toolcalling-merged-demo

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

The young924/toolcalling-merged-demo is a 2 billion parameter Qwen3-based causal language model developed by young924, fine-tuned from unsloth/Qwen3-1.7B-unsloth-bnb-4bit. This model is optimized for tool-calling tasks, leveraging its 32768-token context length to process complex instructions. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning for specialized applications.

Loading preview...

Model Overview

The young924/toolcalling-merged-demo is a 2 billion parameter Qwen3-based language model, developed by young924. It is fine-tuned from the unsloth/Qwen3-1.7B-unsloth-bnb-4bit base model, indicating an optimization for efficiency and performance within its parameter class. The model was trained using Unsloth and Huggingface's TRL library, which facilitated a 2x faster fine-tuning process.

Key Characteristics

  • Architecture: Qwen3-based causal language model.
  • Parameter Count: 2 billion parameters.
  • Context Length: Supports a context length of 32768 tokens.
  • Training Efficiency: Fine-tuned with Unsloth and Huggingface's TRL library for accelerated training.

Primary Use Case

This model is specifically designed and fine-tuned for tool-calling applications. Its architecture and training methodology suggest a focus on accurately interpreting user requests and generating appropriate tool calls, making it suitable for integration into systems requiring automated function execution or API interaction.