app.py

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

model_id = "nvidia/OpenReasoning-Nemotron-1.5B"

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

def chat_api(prompt, max_new_tokens=200, temperature=0.7):
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=max_new_tokens,
        temperature=temperature,
        do_sample=True
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

demo = gr.Interface(
    fn=chat_api,
    inputs=[
        gr.Textbox(label="Prompt", placeholder="Ask me anything..."),
        gr.Slider(50, 512, value=200, step=10, label="Max Tokens"),
        gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
    ],
    outputs="text",
    title="OpenReasoning Nemotron-1.5B API",
    description="Public Hugging Face Space that runs NVIDIA's Nemotron-1.5B model."
)

demo.launch()