JoaoPito/functiongemma-270m-it-simple-tool-calling
TEXT GENERATIONConcurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Jul 4, 2026Architecture:Transformer Featherless Exclusive Cold
The JoaoPito/functiongemma-270m-it-simple-tool-calling model is a 0.3 billion parameter instruction-tuned causal language model, fine-tuned from Google's functiongemma-270m-it. It is optimized for simple tool-calling tasks, leveraging a 32768-token context length. This model is specifically trained for generating responses that involve function calls, making it suitable for applications requiring structured output for external tool interaction.
Loading preview...
Overview
This model, JoaoPito/functiongemma-270m-it-simple-tool-calling, is a specialized version of Google's functiongemma-270m-it model. It has been fine-tuned using the TRL (Transformers Reinforcement Learning) library, specifically employing the SFT (Supervised Fine-Tuning) method.
Key Capabilities
- Function Calling: Optimized for generating responses that include function calls, enabling interaction with external tools or APIs.
- Instruction Following: Inherits instruction-tuning capabilities from its base model, allowing it to follow user prompts effectively.
- Compact Size: With 0.3 billion parameters, it offers a lightweight solution for tool-calling applications.
- Extended Context: Supports a context length of 32768 tokens, useful for complex prompts or multi-turn interactions.
Good for
- Developing applications that require models to interact with external functions or tools.
- Scenarios where a smaller, efficient model is preferred for tool-calling tasks.
- Prototyping and deploying function-calling capabilities with a focus on simplicity and directness.