Devloop4545/functiongemma-270m-it-simple-tool-calling

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Sep 9, 2026Architecture:Transformer Featherless Exclusive Cold

Devloop4545/functiongemma-270m-it-simple-tool-calling is a 0.3 billion parameter language model fine-tuned from Google's functiongemma-270m-it. This model specializes in tool-calling capabilities, leveraging its base architecture for efficient function invocation. It was trained using TRL and supports a context length of 32768 tokens, making it suitable for applications requiring compact yet capable function-calling LLMs.

Loading preview...

Model Overview

This model, Devloop4545/functiongemma-270m-it-simple-tool-calling, is a fine-tuned variant of Google's functiongemma-270m-it model, specifically optimized for tool-calling tasks. With 0.3 billion parameters, it offers a compact solution for integrating LLM-powered function invocation into applications. The model was developed using the TRL (Transformers Reinforcement Learning) library, indicating a focus on efficient and effective fine-tuning.

Key Capabilities

  • Function Calling: Specialized in understanding and generating calls to external tools or functions based on user prompts.
  • Compact Size: At 0.3 billion parameters, it is designed for efficient deployment and lower computational overhead compared to larger models.
  • Extended Context: Supports a context length of 32768 tokens, allowing for processing longer inputs relevant to tool-calling scenarios.

Training Details

The model underwent a Supervised Fine-Tuning (SFT) process using TRL, version 1.12.0. This training approach enhances its ability to accurately interpret user intent and formulate appropriate tool calls. The base model, google/functiongemma-270m-it, provides a strong foundation for these capabilities.