created app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the model and tokenizer
+def load_model():
+    # Load the NuminaMath-72B-CoT model
+    pipe = pipeline(
+        "text-generation",
+        model="AI-MO/NuminaMath-72B-CoT",
+        torch_dtype="auto",
+        device_map="auto"  # Automatically map to available GPU/CPU
+    )
+    return pipe
+
+# Initialize the pipeline
+model_pipeline = load_model()
+
+# Define the function to process inputs
+def solve_math_question(prompt):
+    # Generate output using the model
+    outputs = model_pipeline(prompt, max_new_tokens=1024, do_sample=False)
+    return outputs[0]["generated_text"]
+
+# Define the Gradio interface
+with gr.Blocks() as app:
+    gr.Markdown("# NuminaMath-72B-CoT Math Question Solver")
+    gr.Markdown(
+        "Ask a math-related question, and the model will attempt to solve it with reasoning!"
+    )
+
+    with gr.Row():
+        question = gr.Textbox(
+            label="Your Math Question",
+            placeholder="E.g., For how many values of the constant k will the polynomial x^2 + kx + 36 have two distinct integer roots?",
+        )
+        output = gr.Textbox(label="Model Output")
+
+    submit_button = gr.Button("Solve")
+    submit_button.click(solve_math_question, inputs=question, outputs=output)
+
+# Launch the app
+app.launch()