Overview
Qwen 2 VL 72B Instruct is a highly capable instruction-tuned model with 72 billion parameters, designed for superior performance in coding and mathematics. It supports an extended context length of up to 128K tokens, making it suitable for intricate tasks that require deep contextual understanding.
Specializations
Multimodal capabilities: It can process and generate text and images, making it suitable for tasks like image captioning, image generation, and multimodal question answering.
Large model size: With 72 billion parameters, it offers a large capacity for learning and generating complex text and image outputs.
State-of-the-art performance on visual understanding benchmarks: It demonstrates exceptional performance in understanding and generating visual content.
Integration Guide (Javascript)
To use this model through Portkey, follow these steps:
1. Install Portkey SDK:
npm install --save portkey-ai
2. Set up client with Portkey:
// Import and initialize Portkey
import Portkey from 'portkey-ai'
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY", // Replace with your Portkey API key
virtualKey: "VIRTUAL_KEY" // Your Together AI Virtual Key created in Portkey
})
3. Make a request:
const chatCompletion = await portkey.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'Qwen/Qwen2-VL-72B-Instruct',
});
console.log(chatCompletion.choices);
Model Specifications
Release Date:
18/9/2024
Max. Context Tokens:
128K
Model Size
72B
MMLU:
64.5
%
License:
Open-Source
© 2024 Portkey, Inc. All rights reserved