app.py

import gradio as gr
import torch
from datasets import Dataset
from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer
import pandas as pd
from huggingface_hub import login

def train_model(file, hf_token):
    try:
        # Login to Hugging Face
        if not hf_token:
            return "Please provide a Hugging Face token"
        login(hf_token)
        
        # Load and prepare data
        df = pd.read_csv(file.name)
        dataset = Dataset.from_pandas(df)
        
        # Model setup
        model_name = "facebook/opt-125m"
        tokenizer = AutoTokenizer.from_pretrained(model_name)
        model = AutoModelForCausalLM.from_pretrained(model_name)
        
        # Training configuration
        training_args = TrainingArguments(
            output_dir="./results",
            num_train_epochs=3,
            per_device_train_batch_size=2,
            learning_rate=3e-5,
            save_strategy="epoch",
            push_to_hub=True,
            hub_token=hf_token
        )
        
        # Initialize trainer
        trainer = Trainer(
            model=model,
            args=training_args,
            train_dataset=dataset,
            tokenizer=tokenizer
        )
        
        # Run training
        trainer.train()
        
        return "Training completed successfully!"
        
    except Exception as e:
        return f"Error occurred: {str(e)}"

# Create Gradio interface
demo = gr.Interface(
    fn=train_model,
    inputs=[
        gr.File(label="Upload your CSV file"),
        gr.Textbox(label="Hugging Face Token", type="password")
    ],
    outputs="text",
    title="Product Classifier Training",
    description="Upload your CSV data to train a product classifier model."
)

if __name__ == "__main__":
    demo.launch()