README.md

---
license: other
base_model: google/gemma-2b
model-index:
- name: Octopus-V2-2B
  results: []
tags:
- function calling
---
# Octopus V2: On-device language model for super agent
<p align="center">
<a href="https://huggingface.co/NexaAIDev" target="_blank">Nexa AI HF</a> - <a href="https://www.nexa4ai.com/" target="_blank">Nexa AI Product</a> - <a href="https://nexaai.github.io/octopus" target="_blank">Nexa AI Research Page</a> - <a href="https://nexaai.github.io/octopus" target="_blank">ArXiv</a> - <a href="https://github.com/NexaAI/Octopus" target="_blank">Nexa AI Github</a>  
</p>

<p align="center" width="100%">
<a><img src="Octopus-logo.jpeg" alt="nexa-octopus" style="width: 40%; min-width: 300px; display: block; margin: auto;"></a>
</p>

## Introducing Octopus-V2-2B
Octopus-V2-2B, an advanced open-source language model with 2 billion parameters, represents Nexa AI's research breakthrough in the application of large language models (LLMs) for function calling, specifically tailored for Android APIs. Unlike Retrieval-Augmented Generation (RAG) methods, which require detailed descriptions of potential function arguments—sometimes needing up to tens of thousands of input tokens—Octopus-V2-2B introduces a unique **functional token** strategy for both its training and inference stages. This approach not only allows it to achieve performance levels comparable to GPT-4 but also significantly enhances its inference speed beyond that of RAG-based methods, making it especially beneficial for edge computing devices.

📱 **On-device Applications**:  Octopus-V2-2B is engineered to operate seamlessly on Android devices, extending its utility across a wide range of applications, from Android system management to the orchestration of multiple devices. Further demonstrations of its capabilities are available on the [Nexa AI Research Page](https://nexaai.github.io/octopus), showcasing its adaptability and potential for on-device integration.

🚀 **Inference Speed**: When benchmarked, Octopus-V2-2B demonstrates a remarkable inference speed, outperforming the combination of "Llama7B + RAG solution" by a factor of 36X on a single A100 GPU. Furthermore, compared to GPT-4-turbo (gpt-4-0125-preview), which relies on clusters A100/H100 GPUs, Octopus-V2-2B is 168% faster. This efficiency is attributed to our **functional token** design.

🐙 **Accuracy**: Octopus-V2-2B not only excels in speed but also in accuracy, surpassing the "Llama7B + RAG solution" in function call accuracy by 31%. It achieves a function call accuracy comparable to GPT-4 and RAG + GPT-3.5, with scores ranging between 98% and 100% across benchmark datasets.

💪 **Function Calling Capabilities**: Octopus-V2-2B is capable of in generating individual, nested, and parallel function calls across a variety of complex scenarios.

## Example Use Cases
<p align="center" width="100%">
<a><img src="tool-usage-compressed.png" alt="ondevice" style="width: 80%; min-width: 300px; display: block; margin: auto;"></a>
</p>

You can run the model on a GPU using the following code. 
```python
from gemma.modeling_gemma import GemmaForCausalLM
from transformers import AutoTokenizer
import torch
import time

def inference(input_text):
    start_time = time.time()
    input_ids = tokenizer(input_text, return_tensors="pt").to(model.device)
    input_length = input_ids["input_ids"].shape[1]
    outputs = model.generate(
        input_ids=input_ids["input_ids"], 
        max_length=1024,
        do_sample=False)
    generated_sequence = outputs[:, input_length:].tolist()
    res = tokenizer.decode(generated_sequence[0])
    end_time = time.time()
    return {"output": res, "latency": end_time - start_time}

model_id = "NexaAIDev/android_API_10k_data"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = GemmaForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

input_text = "Take a selfie for me with front camera"
nexa_query = f"Below is the query from the users, please call the correct function and generate the parameters to call the function.\n\nQuery: {input_text} \n\nResponse:"
start_time = time.time()
print("nexa model result:\n", inference(nexa_query))
print("latency:", time.time() - start_time," s")
```

## Evaluation
<p align="center" width="100%">
<a><img src="latency_plot.jpg" alt="ondevice" style="width: 80%; min-width: 300px; display: block; margin: auto; margin-bottom: 20px;"></a>
<a><img src="accuracy_plot.jpg" alt="ondevice" style="width: 80%; min-width: 300px; display: block; margin: auto;"></a>
</p>

## License
This model was trained on commercially viable data and is licensed under the [Nexa AI community license](TODO). 


## References
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},
}
```

## Citation
```
@misc{TODO}
```

## Contact
Please [contact us](dev@nexa4ai.com) to reach out for any issues and comments!