Reka Edge

Reka Edge

Reka Edge

by

Reka

Model ID:

reka-edge

Use This Model

Model Overview

FAQs

Related Links

Overview

Reka Edge is a compact yet powerful 7B parameter model that sets a new state-of-the-art for its size class. It consistently outperforms other leading 7B models like Llama 2, Mistral, and Gemma across a range of benchmarks including MMLU, GSM8K, and HumanEval. Edge also shows strong performance on multilingual tasks. Despite its small size, it approaches the capabilities of much larger models on many tasks. Edge is an ideal choice for developers who need to deploy capable language models in resource-constrained environments or edge devices. Its combination of small size and strong performance makes it well-suited for applications requiring local deployment, low latency, or operation on limited hardware while still maintaining high-quality language understanding and generation.

Specializations

  • State-of-the-art performance in the 7B parameter class.

  • Excels in efficient deployment scenarios.

  • Strong multilingual capabilities despite compact size.

  • Impressive performance on reasoning and coding tasks for its scale.

  • Suitable for edge computing and resource-constrained environments.

  • Approaches capabilities of much larger models on many tasks.

  • Balances model size with high-quality language understanding and generation.

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 Reka 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: 'reka-edge',

});

console.log(chatCompletion.choices);

Model Specifications

Release Date:

15/4/2024

Max. Context Tokens:

64K

Model Size

7B

Knowledge Cut-Off Date:

November 2023

MMLU:

65.7

%

License:

Proprietary

Technical Report/Model Card:

Pricing

$/Million Input Tokens

$

0.1

$/Million Output Tokens

$

0.1

Live updates via Portkey Pricing API. Coming Soon...

© 2024 Portkey, Inc. All rights reserved