---
license: cc-by-nc-4.0
---
# Octo-planner: On-device Language Model for Planner-Action Agents Framework

We're thrilled to introduce the Octo-planner, the latest breakthrough in on-device language models from Nexa AI. Developed for the Planner-Action Agents Framework, Octo-planner enables rapid and efficient planning without the need for cloud connectivity, this model together with [Octopus-V2](https://huggingface.co/NexaAIDev/Octopus-v2) can work on edge devices locally to support AI Agent usages.

### Key Features of Octo-planner:
- **Efficient Planning**: Utilizes fine-tuned plan model based on Gemma-2b (2.51 billion parameters) for high efficiency and low power consumption.
- **Agent Framework**: Separates planning and action, allowing for specialized optimization and improved scalability.
- **Enhanced Accuracy**: Achieves a planning success rate of 98.1% on benchmark dataset, providing reliable and effective performance.
- **On-device Operation**: Designed for edge devices, ensuring fast response times and enhanced privacy by processing data locally.


## Example Usage
Below is a demo of Octo-planner:
<p align="center" width="100%">
<a><img src="1-demo.png" alt="ondevice" style="width: 80%; min-width: 300px; display: block; margin: auto;"></a>
</p>


Run below code to use Octopus Planner for a given question:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "NexaAIDev/octo-planner-2b"
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id)
question = "Find my presentation for tomorrow's meeting, connect to the conference room projector via Bluetooth, increase the screen brightness, take a screenshot of the final summary slide, and email it to all participants"
inputs = f"<|user|>{question}<|end|><|assistant|>"
input_ids = tokenizer(inputs, return_tensors="pt").to(model.device)
outputs = model.generate(
        input_ids=input_ids["input_ids"], 
        max_length=1024,
        do_sample=False)
res = tokenizer.decode(outputs.tolist()[0])
print(f"=== inference result ===\n{res}")
```

## Training Data
We wrote 10 Android API descriptions to used to train the models, see this file for details. Below is one Android API description example
```
def send_email(recipient, title, content):
    """
    Sends an email to a specified recipient with a given title and content.
    Parameters:
    - recipient (str): The email address of the recipient.
    - title (str): The subject line of the email. This is a brief summary or title of the email's purpose or content.
    - content (str): The main body text of the email. It contains the primary message, information, or content that is intended to be communicated to the recipient.
    """
```

## Contact Us
For support or to provide feedback, please [contact us](mailto:octopus@nexa4ai.com).

## License and Citation
Refer to our [license page](https://www.nexa4ai.com/licenses/v2) for usage details. Please cite our work using the below reference for any academic or research purposes.
```
@article{chen2024octoplannerondevicelanguagemodel,
      title={Octo-planner: On-device Language Model for Planner-Action Agents}, 
      author={Wei Chen and Zhiyuan Li and Zhen Guo and Yikang Shen},
      year={2024},
      eprint={2406.18082},
      url={https://arxiv.org/abs/2406.18082}, 
}
```

We thank the Google Gemma team for their amazing models!
```
@misc{gemma-2023-open-models,
  author = {{Gemma Team, Google DeepMind}},
  title = {Gemma: Open Models Based on Gemini Research and Technology},
  url = {https://goo.gle/GemmaReport},  
  year = {2023},
}
```