app.py

import gradio as gr
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
 'vitaliy-sharandin/wiseai',
 load_in_8bit=True,
 device_map = {"": 0}
 )
tokenizer = AutoTokenizer.from_pretrained('vitaliy-sharandin/wiseai')

pipe = pipeline('text-generation', model=model,tokenizer=tokenizer)

def generate_text(prompt):
 result = pipe(prompt, max_length=200, do_sample=True, temperature=0.7, num_return_sequences=1, return_full_text=False)
 return result[0]['generated_text']

iface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
iface.launch()