Mistral 7b Yo Instruct

🚀 mistral_7b_yo_instruct

mistral_7b_yo_instruct is a text generation model in Yorùbá, designed to address the need for high - quality text generation in the Yorùbá language.

🚀 Quick Start

Basic Usage

import requests

API_URL = "https://i8nykns7vw253vx3.us-east-1.aws.endpoints.huggingface.cloud"
headers = {
    "Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "Content-Type": "application/json"
}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

# Prompt content: "Pẹlẹ o. Bawo ni o se wa?" ("Hello. How are you?")	
output = query({
    "inputs": "Pẹlẹ o. Bawo ni o se wa?",
})

# Model response: "O dabo. O jẹ ọjọ ti o dara." ("I am safe. It was a good day.")
print(output)

✨ Features

• Yorùbá Text Generation: Specifically tailored for generating text in the Yorùbá language.

📚 Documentation

Intended uses & limitations

How to use

The provided Python code demonstrates how to interact with the model through an API. You need to replace the hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx in the Authorization header with your actual Hugging Face API token.

Eval results

Coming soon

Limitations and bias

This model is limited by its training dataset, which consists of entity - annotated news articles from a specific time period. As a result, it may not perform well across all use cases in different domains.

Training data

This model is fine - tuned on over 60k instruction - following demonstrations. These demonstrations are built from an aggregation of datasets, including AfriQA, XLSum, MENYO - 20k, and translations of [Alpaca - gpt4](https://huggingface.co/datasets/vicgalle/alpaca - gpt4).

Use and safety

We emphasize that mistral_7b_yo_instruct is intended only for research purposes and is not ready to be deployed for general use. This is mainly because we have not designed adequate safety measures.

📄 License

This model is licensed under the afl - 3.0 license.