Mistralai Sentiment Nuclear

🚀 MistralAI 7B Text Classification Model

A fine - tuned MistralAI 7B model for text classification on nuclear energy data from Twitter/X, achieving 94% accuracy.

🚀 Quick Start

This MistralAI 7B model was fine - tuned on nuclear energy data sourced from Twitter/X. It has achieved a classification accuracy of 94%. There are 3 labels: {0: Negative, 1: Neutral, 2: Positive}.

⚠️ Important Note

You need sufficient GPU to run this model.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer
from transformers import pipeline
from transformers import AutoModelForSequenceClassification
import torch

checkpoint = 'kumo24/mistralai-sentiment-nuclear'
tokenizer=AutoTokenizer.from_pretrained(checkpoint)
id2label = {0: "negative", 1: "neutral", 2: "positive"}
label2id = {"negative": 0, "neutral": 1, "positive": 2}
    

if tokenizer.pad_token is None:
    tokenizer.add_special_tokens({'pad_token': '[PAD]'})

model = AutoModelForSequenceClassification.from_pretrained(checkpoint, 
                                                       num_labels=3,
                                                       id2label=id2label, 
                                                       label2id=label2id,
                                                       device_map='auto')

sentiment_task = pipeline("sentiment-analysis", 
                          model=model, 
                          tokenizer=tokenizer)

print(sentiment_task("Michigan Wolverines are Champions, Go Blue!"))

This example demonstrates how to use the model, and it was tested on an 8 GB Nvidia - RTX 4060.

📄 License

This project is licensed under the Apache 2.0 license.