Mistral 7b

Approved Data Classifications

Description

Mistral-7B-v0.3 is an advanced language model developed by Mistral AI, specifically fine-tuned for instruction-based tasks to enhance its language generation and understanding capabilities. Released in May 2024, this model features a transformer architecture with an extended vocabulary of 32,768 tokens, allowing it to process a wider range of inputs and generate more nuanced responses. Key innovations include the implementation of grouped-query attention for faster inference and support for function calling, enabling the model to execute predefined functions during language processing. This makes Mistral-7B-v0.3 particularly effective for applications requiring coherent dialogue, task completion, and interactive user experiences. Its design is optimized for various scenarios, from customer service chatbots to educational tools, making it a versatile choice for developers looking to leverage advanced AI capabilities in their applications.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
mistral-7b-instruct	October 2023	Text	Text	32,000	$0.15/1M input $0.20/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "mistral-7b-instruct",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.chat.completions.create(
      model="mistral-7b-instruct", # model to send to the proxy
      messages = [
          { role: "system", content: "You are a helpful assistant." },
          {
              "role": "user",
              "content": "Write a haiku about an Alligator."
          }
      ]
  )

  print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "mistral-7b-instruct",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)