Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,45 @@
+
+import gradio as gr
+import ctranslate2
+from transformers import AutoTokenizer
+
+# Define the model and tokenizer loading
+model_prompt = "Solve the following mathematical problem: "
+tokenizer = AutoTokenizer.from_pretrained("AI-MO/NuminaMath-7B-TIR")
+model_path = "/kaggle/working/deepseek-math-Numina"
+generator = ctranslate2.Generator(model_path, device="cpu", compute_type="int8")
+
+# Function to generate predictions using the model
+def get_prediction(question):
+    input_text = model_prompt + question
+    input_tokens = tokenizer.tokenize(input_text)
+    results = generator.generate_batch([input_tokens])
+    output_tokens = results[0].sequences[0]
+    predicted_answer = tokenizer.convert_tokens_to_string(output_tokens)
+    return predicted_answer
+
+# Gradio interface for user input and output
+def gradio_interface(question, correct_answer):
+    predicted_answer = get_prediction(question)
+    return {
+        "question": question,
+        "predicted_answer": predicted_answer,
+        "correct_answer": correct_answer,
+    }
+
+# Gradio app setup
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Textbox(label="Math Question"),
+        gr.Textbox(label="Correct Answer"),
+    ],
+    outputs=[
+        gr.JSON(label="Results")
+    ],
+    title="Math Question Solver",
+    description="Enter a math question to get the model prediction."
+)
+
+if __name__ == "__main__":
+    interface.launch()