Mistral 7B Instruct v0.2

Mistral 7B Instruct v0.2

Mistral 7B Instruct v0.2

by

Mistral

Model ID:

mistral.mistral-7b-instruct-v0:2

Use This Model

Model Overview

FAQs

Related Links

Overview

Mistral 7B Instruct v0.2 is a refined 7 billion parameter model optimized for instruction-following tasks. It excels in generating coherent responses and engaging in open-ended dialogues, making it a strong choice for chatbot development and virtual assistants, outperforming many of its peers in various benchmarks.

Specializations

  • Instruction-following capabilities: It is fine-tuned to follow instructions effectively, making it suitable for tasks like summarization, translation, and content generation.

  • Efficient inference: It offers fast inference speeds, making it suitable for real-time applications.

  • Open-source availability: Its open-source nature allows for customization and further development by the community.

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 AWS Bedrock 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: 'mistral.mistral-7b-instruct-v0:2',

    max_tokens: 250 // Required field for AWS Bedrock

});

console.log(chatCompletion.choices);

Live API Statistics and Performace Metrics

LMSys Arena Elo Score:

1072

Arena Score

LMSys Leaderboard Rank:

95

Arena Rank

Evaluates LLMs through a combination of user feedback and automated scoring systems.

HumanEval Leaderboard Score:

Leaderboard Score

26.2

%

A specific benchmark score measuring the model's accuracy in executing code generations.

Model Specifications

Release Date:

11/12/2023

Max. Context Tokens:

32K

Max. Output Tokens:

4K

Model Size

7B

Knowledge Cut-Off Date:

December 2023

MMLU:

60.1

%

License:

Open-Source

Technical Report/Model Card:

LMSys Elo Score

1072

Pricing

$/Million Input Tokens

$

0.2

$/Million Output Tokens

$

0.2

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

© 2024 Portkey, Inc. All rights reserved