Octopus V2
On-Device 2B LLMs for actions, outperform GPT-4.
Octopus V2 Highlights
On-device model
A 2 billion-parameter language model developed for high-performance function calling on edge devices.
Functional tokens
Uses a novel 'functional token' strategy to reduce context length by 95%.
Blazing fast
Demonstrates a 35x faster inference speed compared to the RAG solution, and is 168% faster than GPT-4 Turbo.
Highly accurate
Achieves 98%+ function call accuracy, surpassing previous models and matching the performance of GPT-4.
Octopus V2 Demo Video
On-device language model for super agent
On-device language model for super agent: Octopus-V2-2B, an advanced open-source language model with 2 billion parameters, represents Nexa AI's research breakthrough in applying large language models (LLMs) for function calling. 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 boosts its inference speed beyond that of RAG-based methods.
Explore our collection of 200+ Premium Webflow Templates