Mistral 7b Wiki

🚀 Mistral-7B-Wiki Model Card

This is a fine-tuned model based on the Mistral-7B model, specifically optimized for Korean text generation.

🚀 Quick Start

You can load the model directly or use a pipeline for text generation. Here are the code examples:

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shleeeee/mistral-7b-wiki")
model = AutoModelForCausalLM.from_pretrained("shleeeee/mistral-7b-wiki")

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="shleeeee/mistral-7b-wiki")

✨ Features

• Fine-tuned for Korean: This model is fine-tuned using Korean data, making it more suitable for Korean text generation tasks.
• Based on Mistral-7B-v0.1: It leverages the powerful architecture of Mistral-7B-v0.1 and further optimizes it for specific tasks.

📦 Installation

The installation steps are included in the usage code examples above. You need to have the transformers library installed. You can install it using the following command:

pip install transformers

📚 Documentation

Model Details

Dataset

The model is trained on a Korean Custom Dataset.

Prompt template: Mistral

<s>[INST]{['instruction']}[/INST]{['output']}</s>

Evaluation