app.py

import gradio as gr

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

base_model = "google/gemma-2b-it"
adapter_model = "isimorfizam/logs"

model = AutoModelForCausalLM.from_pretrained(base_model)
model = PeftModel.from_pretrained(model, adapter_model)
tokenizer = AutoTokenizer.from_pretrained(base_model)

model = model.to("cuda")

def predict(question):
    
    #input_pretext = 'Answer the following question for me.'
    input_text = question
    input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
    
    outputs = model.generate(**input_ids, max_length = 100)
    return tokenizer.decode(outputs[0])


gradio_app = gr.Interface(
    predict,
    inputs=str,
    outputs=str,
    title='QA',
)

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