made code

app.py

@@ -1,63 +1,194 @@
-
 import gradio as gr
 import ctranslate2
 from transformers import AutoTokenizer
 from huggingface_hub import snapshot_download
-from codeexecutor import postprocess_completion,get_majority_vote
-
+from codeexecutor import get_majority_vote
+import re
+import os
 # Define the model and tokenizer loading
-model_prompt = "Solve the following mathematical problem: "
+model_prompt = "Explain and solve the following mathematical problem step by step, showing all work: "
 tokenizer = AutoTokenizer.from_pretrained("AI-MO/NuminaMath-7B-TIR")
 model_path = snapshot_download(repo_id="Makima57/deepseek-math-Numina")
 generator = ctranslate2.Generator(model_path, device="cpu", compute_type="int8")
-iterations=10
+iterations = 10
 
 # 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])
+    results = generator.generate_batch(
+        [input_tokens],
+        max_length=512,
+        sampling_temperature=0.7,
+        sampling_topk=40,
+    )
     output_tokens = results[0].sequences[0]
     predicted_answer = tokenizer.convert_tokens_to_string(output_tokens)
     return predicted_answer
 
-# Function to perform majority voting across multiple predictions
-def majority_vote(question, num_iterations=10):
+# Function to parse the prediction to extract the answer and steps
+def parse_prediction(prediction):
+    lines = prediction.strip().split('\n')
+    answer = None
+    steps = []
+    for line in lines:
+        # Check for "Answer:" or "answer:"
+        match = re.match(r'^\s*(?:Answer|answer)\s*[:=]\s*(.*)', line)
+        if match:
+            answer = match.group(1).strip()
+        else:
+            steps.append(line)
+    if answer is None:
+        # If no "Answer:" found, assume last line is the answer
+        answer = lines[-1].strip()
+        steps = lines[:-1]
+    steps_text = '\n'.join(steps).strip()
+    return answer, steps_text
+
+# Function to perform majority voting and get steps
+def majority_vote_with_steps(question, num_iterations=10):
     all_predictions = []
-    all_answer=[]
+    all_answers = []
+    steps_list = []
+
     for _ in range(num_iterations):
         prediction = get_prediction(question)
-        answer=postprocess_completion(prediction,True,True)
+        answer, steps = parse_prediction(prediction)
         all_predictions.append(prediction)
-        all_answer.append(answer)
-    majority_voted_pred = max(set(all_predictions), key=all_predictions.count)
-    majority_voted_ans=get_majority_vote(all_answer)
-    return majority_voted_pred, all_predictions,majority_voted_ans
+        all_answers.append(answer)
+        steps_list.append(steps)
+
+    # Get the majority voted answer
+    majority_voted_ans = get_majority_vote(all_answers)
+
+    # Find the steps corresponding to the majority voted answer
+    for i, ans in enumerate(all_answers):
+        if ans == majority_voted_ans:
+            steps_solution = steps_list[i]
+            break
+    else:
+        steps_solution = "No steps found"
+
+    return majority_voted_ans, steps_solution
 
 # Gradio interface for user input and output
 def gradio_interface(question, correct_answer):
-    final_prediction, all_predictions,final_answer = majority_vote(question, iterations)
-    return {
-        "Question": question,
-        "Generated Answers (10 iterations)": all_predictions,
-        "Majority-Voted Prediction": final_prediction,
-        "Correct solution": correct_answer,
-        "Majority answer": final_answer
+    final_answer, steps_solution = majority_vote_with_steps(question, iterations)
+    return question, final_answer, steps_solution, correct_answer
+
+# Custom CSS for enhanced design (unchanged)
+custom_css = """
+    body {
+        background-color: #fafafa;
+        font-family: 'Open Sans', sans-serif;
+    }
+    .gradio-container {
+        background-color: #ffffff;
+        border: 3px solid #007acc;
+        border-radius: 15px;
+        padding: 20px;
+        box-shadow: 0 8px 20px rgba(0, 0, 0, 0.15);
+        max-width: 800px;
+        margin: 50px auto;
+    }
+    h1 {
+        font-family: 'Poppins', sans-serif;
+        color: #007acc;
+        font-weight: bold;
+        font-size: 32px;
+        text-align: center;
+        margin-bottom: 20px;
+    }
+    p {
+        font-family: 'Roboto', sans-serif;
+        font-size: 18px;
+        color: #333;
+        text-align: center;
+        margin-bottom: 15px;
     }
+    input, textarea {
+        font-family: 'Montserrat', sans-serif;
+        font-size: 16px;
+        padding: 10px;
+        border: 2px solid #007acc;
+        border-radius: 10px;
+        background-color: #f1f8ff;
+        margin-bottom: 15px;
+    }
+    #math_question, #correct_answer {
+        font-size: 20px;
+        font-family: 'Poppins', sans-serif;
+        font-weight: 500px;
+        color: #007acc;
+        margin-bottom: 5px;
+        display: inline-block;
+    }
+    
+    textarea {
+        min-height: 150px;
+    }
+    .gr-button-primary {
+        background-color: #007acc !important;
+        color: white !important;
+        border-radius: 10px !important;
+        font-size: 18px !important;
+        font-weight: bold !important;
+        padding: 10px 20px !important;
+        font-family: 'Montserrat', sans-serif !important;
+        transition: background-color 0.3s ease !important;
+    }
+    .gr-button-primary:hover {
+        background-color: #005f99 !important;
+    }
+    .gr-button-secondary {
+        background-color: #f44336 !important;
+        color: white !important;
+        border-radius: 10px !important;
+        font-size: 18px !important;
+        font-weight: bold !important;
+        padding: 10px 20px !important;
+        font-family: 'Montserrat', sans-serif !important;
+        transition: background-color 0.3s ease !important;
+    }
+    .gr-button-secondary:hover {
+        background-color: #c62828 !important;
+    }
+    .gr-output {
+        background-color: #e0f7fa;
+        border: 2px solid #007acc;
+        border-radius: 10px;
+        padding: 15px;
+        font-size: 16px;
+        font-family: 'Roboto', sans-serif;
+        font-weight: bold;
+        color: #00796b;
+    }
+"""
+
+# Define the directory path
+flagging_dir = "./flagged_data"
+
+# Create the directory if it doesn't exist
+if not os.path.exists(flagging_dir):
+    os.makedirs(flagging_dir)
 
-# Gradio app setup
+# Gradio app setup with flagging
 interface = gr.Interface(
     fn=gradio_interface,
     inputs=[
-        gr.Textbox(label="Math Question"),
-        gr.Textbox(label="Correct Answer"),
+        gr.Textbox(label="🧠 Math Question", placeholder="Enter your math question here...", elem_id="math_question"),
     ],
     outputs=[
-        gr.JSON(label="Results"),  # Display the results in a JSON format
+        gr.Textbox(label="Majority-Voted Answer", interactive=False),  # Non-editable
+        gr.Textbox(label="Steps to Solve", interactive=False),  # Non-editable
+        gr.Textbox(label="✅ Correct Solution", interactive=True),  # Editable textbox for correct solution
     ],
-    title="Math Question Solver",
-    description="Enter a math question to get the model prediction and see all generated answers.",
+    title="🔢 Math Question Solver",
+    description="Enter a math question to get the model's majority-voted answer and steps to solve the problem.",
+    css=custom_css,  # Apply custom CSS
+    flagging_dir=flagging_dir,  # Directory to save flagged data
+    allow_flagging="auto"  # Allow users to auto flag data
 )
 
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()

temp.py

@@ -0,0 +1,191 @@
+import gradio as gr
+import ctranslate2
+from transformers import AutoTokenizer
+from huggingface_hub import snapshot_download
+from codeexecutor import get_majority_vote
+import re
+
+# Define the model and tokenizer loading
+model_prompt = "Explain and solve the following mathematical problem step by step, showing all work: "
+tokenizer = AutoTokenizer.from_pretrained("AI-MO/NuminaMath-7B-TIR")
+model_path = snapshot_download(repo_id="Makima57/deepseek-math-Numina")
+generator = ctranslate2.Generator(model_path, device="cpu", compute_type="int8")
+iterations = 10
+
+# 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],
+        max_length=512,
+        sampling_temperature=0.7,
+        sampling_topk=40,
+    )
+    output_tokens = results[0].sequences[0]
+    predicted_answer = tokenizer.convert_tokens_to_string(output_tokens)
+    return predicted_answer
+
+# Function to parse the prediction to extract the answer and steps
+def parse_prediction(prediction):
+    lines = prediction.strip().split('\n')
+    answer = None
+    steps = []
+    for line in lines:
+        # Check for "Answer:" or "answer:"
+        match = re.match(r'^\s*(?:Answer|answer)\s*[:=]\s*(.*)', line)
+        if match:
+            answer = match.group(1).strip()
+        else:
+            steps.append(line)
+    if answer is None:
+        # If no "Answer:" found, assume last line is the answer
+        answer = lines[-1].strip()
+        steps = lines[:-1]
+    steps_text = '\n'.join(steps).strip()
+    return answer, steps_text
+
+# Function to perform majority voting and get steps
+def majority_vote_with_steps(question, num_iterations=10):
+    all_predictions = []
+    all_answers = []
+    steps_list = []
+
+    for _ in range(num_iterations):
+        prediction = get_prediction(question)
+        answer, steps = parse_prediction(prediction)
+        all_predictions.append(prediction)
+        all_answers.append(answer)
+        steps_list.append(steps)
+
+    # Get the majority voted answer
+    majority_voted_ans = get_majority_vote(all_answers)
+
+    # Find the steps corresponding to the majority voted answer
+    for i, ans in enumerate(all_answers):
+        if ans == majority_voted_ans:
+            steps_solution = steps_list[i]
+            break
+    else:
+        steps_solution = "No steps found"
+
+    return majority_voted_ans, steps_solution
+
+# Gradio interface for user input and output
+def gradio_interface(question, correct_answer):
+    final_answer, steps_solution = majority_vote_with_steps(question, iterations)
+    return {
+        "Question": question,
+        "Majority-Voted Answer": final_answer,
+        "Steps to Solve": steps_solution,
+        "Correct Solution": correct_answer
+    }
+
+# Custom CSS for enhanced design (unchanged)
+custom_css = """
+    body {
+        background-color: #fafafa;
+        font-family: 'Open Sans', sans-serif;
+    }
+    .gradio-container {
+        background-color: #ffffff;
+        border: 3px solid #007acc;
+        border-radius: 15px;
+        padding: 20px;
+        box-shadow: 0 8px 20px rgba(0, 0, 0, 0.15);
+        max-width: 800px;
+        margin: 50px auto;
+    }
+    h1 {
+        font-family: 'Poppins', sans-serif;
+        color: #007acc;
+        font-weight: bold;
+        font-size: 32px;
+        text-align: center;
+        margin-bottom: 20px;
+    }
+    p {
+        font-family: 'Roboto', sans-serif;
+        font-size: 18px;
+        color: #333;
+        text-align: center;
+        margin-bottom: 15px;
+    }
+    input, textarea {
+        font-family: 'Montserrat', sans-serif;
+        font-size: 16px;
+        padding: 10px;
+        border: 2px solid #007acc;
+        border-radius: 10px;
+        background-color: #f1f8ff;
+        margin-bottom: 15px;
+    }
+    #math_question, #correct_answer {
+        font-size: 20px;
+        font-family: 'Poppins', sans-serif;
+        font-weight: 500px;
+        color: #007acc;
+        margin-bottom: 5px;
+        display: inline-block;
+    }
+    
+    textarea {
+        min-height: 150px;
+    }
+    .gr-button-primary {
+        background-color: #007acc !important;
+        color: white !important;
+        border-radius: 10px !important;
+        font-size: 18px !important;
+        font-weight: bold !important;
+        padding: 10px 20px !important;
+        font-family: 'Montserrat', sans-serif !important;
+        transition: background-color 0.3s ease !important;
+    }
+    .gr-button-primary:hover {
+        background-color: #005f99 !important;
+    }
+    .gr-button-secondary {
+        background-color: #f44336 !important;
+        color: white !important;
+        border-radius: 10px !important;
+        font-size: 18px !important;
+        font-weight: bold !important;
+        padding: 10px 20px !important;
+        font-family: 'Montserrat', sans-serif !important;
+        transition: background-color 0.3s ease !important;
+    }
+    .gr-button-secondary:hover {
+        background-color: #c62828 !important;
+    }
+    .gr-output {
+        background-color: #e0f7fa;
+        border: 2px solid #007acc;
+        border-radius: 10px;
+        padding: 15px;
+        font-size: 16px;
+        font-family: 'Roboto', sans-serif;
+        font-weight: bold;
+        color: #00796b;
+    }
+"""
+
+# Gradio app setup
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Textbox(label="🧠 Math Question", placeholder="Enter your math question here...", elem_id="math_question"),
+         
+    ],
+    outputs=[
+        gr.Textbox(label="Majority-Voted Answer", interactive=False),  # Non-editable
+        gr.Textbox(label="Steps to Solve", interactive=False),  # Non-editable
+        gr.Textbox(label="✅ Correct Solution", interactive=True),  # Editable textbox for correct solution
+    ],
+    title="🔢 Math Question Solver",
+    description="Enter a math question to get the model's majority-voted answer and steps to solve the problem.",
+    css=custom_css  # Apply custom CSS
+)
+
+if _name_ == "_main_":
+    interface.launch()