app.py

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

peft_model_id = "burberg92/resume_summary"
config = PeftConfig.from_pretrained(peft_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    return_dict=True,
    load_in_8bit=False,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

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


def make_inference(resume):
  batch = tokenizer(f"Write an excecutive summary based off this resume.\n\n### Resume:\n{resume}", 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__":
    import gradio as gr

    gr.Interface(
    make_inference,
    [
        gr.inputs.Textbox(lines=2, label="Resume"),
    ],
    gr.outputs.Textbox(label="Executive Summary"),
    title="Exective Summary Generator",
    description="This generates an Exectutive Summary from a Resume",
).launch()