app.py

import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

peft_model_id = f"PanoEvJ/GenAIGenAI-CoverLetter"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    return_dict=True,
    load_in_8bit=True,
    device_map="auto",
)
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(job_posting):
  batch = tokenizer(f"Below is a job posting, please write a cover letter for this product.\n\n### Job posting:\n{job_posting} \n\n### Cover letter:\n", return_tensors='pt')

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

  return 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=40, label="Job posting"),
        ],
        gr.outputs.Textbox(label="Cover letter"),
        title="GenAI_CoverLetter",
        description="GenAI_CoverLetter is a tool that generates cover letters for job postings.",
    ).launch()