app.py

import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
from IPython.display import display, Markdown

peft_model_id = f"adamtappis/marketing_emails_model"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=False)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id)

def make_inference(product, description):
  batch = tokenizer(f"### INSTRUCTION\nBelow is a product and description, please write a marketing email for this product.\n\n### Product:\n{product}\n### Description:\n{description}\n\n### Marketing Email:\n", return_tensors='pt')

  with torch.cuda.amp.autocast():
    output_tokens = model.generate(**batch, max_new_tokens=200)

  display(Markdown((tokenizer.decode(output_tokens[0], skip_special_tokens=True))))

if __name__ == "__main__":
    # make a gradio interface
    import gradio as gr

    gr.Interface(
        make_inference,
        [
            gr.inputs.Textbox(lines=1, label="Product Name"),
            gr.inputs.Textbox(lines=1, label="Product Description"),
        ],
        gr.outputs.Textbox(label="Email"),
        title="🗣️Marketing Email Generator📄",
        description="🗣️Marketing Email Generator📄 is a tool that allows you to generate marketing emails for different products",
    ).launch()