---
base_model: google/functiongemma-270m-it
library_name: transformers
tags:
- function-calling
- agents
- gemma
- text-generation
- tiny-agent
license: gemma
language:
- en
pipeline_tag: text-generation
---

# Tiny Agent: FunctionGemma-270m-IT (Fine-Tuned)

This is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it) optimized for reliable function calling. 
It was trained as part of the "Tiny Agent Lab" project to distill the capabilities of larger models into a highly efficient 270M parameter model.

## Model Description

- **Model Type:** Causal LM (Gemma)
- **Language(s):** English
- **License:** Gemma Terms of Use
- **Finetuned from:** google/functiongemma-270m-it

## Capabilities

This model is designed to:
1.  **Detect User Intent:** Accurately identify when a tool call is needed.
2.  **Generate Function Calls:** Output valid `<start_function_call>` XML/JSON blocks.
3.  **Refuse Out-of-Scope Requests:** Politely decline requests for which no tool is available.
4.  **Ask Clarification:** Request missing parameter values interactively.

## Performance (V4 Evaluation)

On a held-out test set of 100 diverse queries:
- **Overall Accuracy:** 71%
- **Tool Selection Precision:** 88%
- **Tool Selection Recall:** 94%
- **F1 Score:** 0.91

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "CuriousDragon/functiongemma-270m-tiny-agent"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)

# ... (Add your inference code here)
```

## Intended Use

This model is intended for research and educational purposes in building efficient agentic systems. It works best when provided with a clear system prompt defining the available tools.