app.py

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

@spaces.GPU
def greet(name):
    pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
    messages = [
        {
            "role": "system",
            "content": "You are a friendly chatbot who always responds in the Professsional way",
        },
        {"role": "user", "content": name},
    ]
    prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    outputs = pipe(prompt, max_new_tokens=2048, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)

    return outputs[0]["generated_text"]

demo = gr.Interface(
    fn=greet,
    inputs=["text"],
    outputs=["text"],
)

demo.launch(share=True)