zard96/toolcalling-merged-demo

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

The zard96/toolcalling-merged-demo is a 2 billion parameter Qwen3-based causal language model developed by zard96, fine-tuned from unsloth/Qwen3-1.7B-unsloth-bnb-4bit. It was trained 2x faster using Unsloth and Huggingface's TRL library, offering a 32768 token context length. This model is optimized for efficient performance, leveraging accelerated training methods for its Qwen3 architecture.

Loading preview...

Model Overview

The zard96/toolcalling-merged-demo is a 2 billion parameter language model built upon the Qwen3 architecture. It was developed by zard96 and fine-tuned from the unsloth/Qwen3-1.7B-unsloth-bnb-4bit base model. A key characteristic of this model is its training methodology, which utilized Unsloth and Huggingface's TRL library to achieve a 2x faster training speed.

Key Characteristics

  • Architecture: Qwen3-based, providing a robust foundation for language tasks.
  • Parameter Count: 2 billion parameters, balancing performance with computational efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens, enabling processing of longer inputs.
  • Training Efficiency: Benefits from accelerated training via Unsloth, making it a potentially more resource-efficient option for deployment.

Good For

  • Developers seeking a Qwen3-based model with optimized training origins.
  • Applications requiring a balance of model size and a generous context window.
  • Use cases where efficient model development and deployment are priorities, leveraging the Unsloth training advantages.