wip

README.md

@@ -1,18 +1,95 @@
 ---
 license: other
-base_model: google/gemma-7b
+base_model: google/gemma-2b
 model-index:
-- name: Octopus-v1-7b
+- name: Octopus-V2-2B
   results: []
 tags:
 - function calling
 ---
-# Octopus V1: On-device language model for function calling of software APIs
+# 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://github.com/NexaAI/Octopus" target="_blank">Nexa AI Github</a>  
+<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.png" alt="nexa-octopus" style="width: 40%; min-width: 300px; display: block; margin: auto;"></a>
+<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!