app.py

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

model_name = "openai-community/gpt-oss-20b"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

def chat(message, history):
    inputs = tokenizer(message, return_tensors="pt").to(model.device)
    outputs = model.generate(
        **inputs,
        max_length=200,
        do_sample=True,
        temperature=0.7,
        top_p=0.9
    )
    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return reply

iface = gr.ChatInterface(fn=chat)
iface.launch()