Model Overview

The pstic/toolcalling-merged-demo is a 2 billion parameter language model developed by pstic, specifically fine-tuned for tool-calling capabilities. It is based on the Qwen3 architecture and was initialized from the unsloth/Qwen3-1.7B-unsloth-bnb-4bit model.

Key Characteristics

• Architecture: Qwen3-based, a causal language model.
• Parameter Count: 2 billion parameters, offering a balance between performance and efficiency.
• Context Length: Features a substantial 32768 token context window, allowing for processing and understanding of lengthy prompts and complex tool-use scenarios.
• Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
• License: Released under the Apache-2.0 license, promoting open and flexible use.

Primary Use Case

This model is specifically optimized for tool-calling applications, where it can interpret user requests and generate appropriate tool invocations. Its large context window is particularly beneficial for understanding intricate instructions and managing multi-step tool-use workflows.