app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Define the prediction function
def predict(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Create the Gradio interface
iface = gr.Interface(
    fn=predict,
    inputs=[gr.Textbox(lines=5, label="Input Text")],
    outputs=[gr.Textbox(label="Generated Text")],
    title="DeepSeek-R1-Distill-Qwen-1.5B Text Generation",
    description="Enter text and the model will generate a continuation.",
)

if __name__ == "__main__":
    iface.launch()