app.py

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

model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

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

def chat(message):
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": message}
    ]
    prompt = f"<|user|>\n{message}\n<|assistant|>\n"
    output = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.7)[0]["generated_text"]
    return output.split("<|assistant|>\n")[-1].strip()

iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="TinyLlama Chat")
iface.launch()