app.py

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

MODEL_ID = "Qwen/Qwen2.5-Coder-1.5B-Instruct"  # or your model
device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, 
    torch_dtype=torch.float16 if device == "cuda" else torch.float32
)
model.to(device)

def generate(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.2)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

demo = gr.Interface(
    fn=generate,
    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
    outputs=gr.Textbox(lines=2, max_lines=30)  # auto-expands up to 30 lines
)

demo.launch()