NexaAIDev
/

Octopus-v2

Text Generation

function calling

on-device language model

text-generation-inference

Model card Files Files and versions Community

Zack Zhiyuan Li commited on Apr 3

Commit

cf57a97

•

1 Parent(s): 9be03ce

add logo

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -21,9 +21,8 @@ language:
 </p>
 <p align="center" width="100%">
-  <iframe width="560" height="315" src="https://www.youtube.com/embed/jhM0D0OObOw?autoplay=1&mute=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen style="display: block; margin: auto;"></iframe>
 </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.

 </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.