Nipun/vayuchat-gemma3-270m-tools-v1
Nipun/vayuchat-gemma3-270m-tools-v1 is a 270 million parameter language model, fine-tuned from unsloth/gemma-3-270m-it. Developed by Nipun, this model is specifically trained for tool-use planning, leveraging Supervised Fine-Tuning (SFT) with a 32K context length. It is designed to enhance capabilities in scenarios requiring structured interaction and planning with external tools.
Loading preview...
Model Overview
Nipun/vayuchat-gemma3-270m-tools-v1 is a compact 270 million parameter language model, fine-tuned from the unsloth/gemma-3-270m-it base model. This iteration, developed by Nipun, focuses on enhancing tool-use capabilities through Supervised Fine-Tuning (SFT).
Key Capabilities
- Tool-Use Planning: The model is specifically trained to facilitate planning and interaction with external tools, making it suitable for applications requiring structured outputs or function calls.
- Compact Size: With 270 million parameters, it offers a lightweight solution for deployment in resource-constrained environments while maintaining specialized functionality.
- Extended Context Window: It supports a context length of 32,768 tokens, allowing for processing longer inputs and more complex tool-use scenarios.
Training Details
The model underwent Supervised Fine-Tuning (SFT) using the TRL framework (version 0.29.1). The training process utilized Transformers 4.57.6, Pytorch 2.7.1+cu128, and Datasets 5.0.0.
Good For
- Applications requiring a small, efficient model for tool-use orchestration.
- Scenarios where a model needs to generate structured outputs to interact with APIs or external systems.
- Research and development in efficient tool-augmented language models.