Update app.py

app.py

@@ -35,7 +35,6 @@ def setup_cyberpunk_style():
             from {text-shadow: 0 0 5px #00ff9d, 0 0 10px #00ff9d;}
             to {text-shadow: 0 0 15px #00b8ff, 0 0 20px #00b8ff;}
         }
-
         .stButton > button {
             font-family: 'Orbitron', sans-serif;
             background: linear-gradient(45deg, #00ff9d, #00b8ff);
@@ -51,7 +50,6 @@ def setup_cyberpunk_style():
             transform: scale(1.1);
             box-shadow: 0 0 20px rgba(0, 255, 157, 0.5);
         }
-
         .progress-bar-container {
             background: rgba(0, 0, 0, 0.5);
             border-radius: 15px;
@@ -115,12 +113,20 @@ def initialize_model(model_name="gpt2"):
     tokenizer.pad_token = tokenizer.eos_token
     return model, tokenizer
 
-# Load Dataset Function
-def load_dataset(data_source="demo", tokenizer=None):
+# Load Dataset Function with Uploaded File Option
+def load_dataset(data_source="demo", tokenizer=None, uploaded_file=None):
     if data_source == "demo":
         data = ["Sample text data for model training. This can be replaced with actual data for better performance."]
+    elif uploaded_file is not None:
+        if uploaded_file.name.endswith(".txt"):
+            data = [uploaded_file.read().decode("utf-8")]
+        elif uploaded_file.name.endswith(".csv"):
+            import pandas as pd
+            df = pd.read_csv(uploaded_file)
+            data = df[df.columns[0]].tolist()  # assuming first column is text data
     else:
-        data = ["Loaded data from uploaded text file."]
+        data = ["No file uploaded. Please upload a dataset."]
+    
     dataset = prepare_dataset(data, tokenizer)
     return dataset
 
@@ -160,53 +166,35 @@ def main():
     with st.sidebar:
         st.markdown("### Configuration Panel")
     
-    # Hugging Face API Token Input
-    hf_token = st.text_input("Enter your Hugging Face Token", type="password")
-    if hf_token:
-        api = HfApi()
-        api.set_access_token(hf_token)
-        st.success("Hugging Face token added successfully!")
-
-    # Training Parameters
-    training_epochs = st.slider("Training Epochs", min_value=1, max_value=5, value=3)
-    batch_size = st.slider("Batch Size", min_value=2, max_value=8, value=4)
-    model_choice = st.selectbox("Model Selection", ("gpt2", "distilgpt2", "gpt2-medium"))
-    
-    # Dataset Source Selection
-    data_source = st.selectbox("Data Source", ("demo", "uploaded file"))
-    if data_source == "uploaded file":
-        uploaded_file = st.file_uploader("Upload a text file", type=["txt", "csv"])
-    
-    custom_learning_rate = st.slider("Learning Rate", min_value=1e-6, max_value=5e-4, value=3e-5, step=1e-6)
-
-    # Advanced Settings Toggle
-    advanced_toggle = st.checkbox("Advanced Training Settings")
-    if advanced_toggle:
-        warmup_steps = st.slider("Warmup Steps", min_value=0, max_value=500, value=100)
-        weight_decay = st.slider("Weight Decay", min_value=0.0, max_value=0.1, step=0.01, value=0.01)
-    else:
-        warmup_steps = 100
-        weight_decay = 0.01
+        # Hugging Face API Token Input
+        hf_token = st.text_input("Enter your Hugging Face Token", type="password")
+        if hf_token:
+            api = HfApi()
+            api.set_access_token(hf_token)
+            st.success("Hugging Face token added successfully!")
+
+        # Training Parameters
+        training_epochs = st.slider("Training Epochs", min_value=1, max_value=5, value=3)
+        batch_size = st.slider("Batch Size", min_value=2, max_value=8, value=4)
+        model_choice = st.selectbox("Model Selection", ("gpt2", "distilgpt2", "gpt2-medium"))
+        
+        # Dataset Source Selection
+        data_source = st.selectbox("Data Source", ("demo", "uploaded file"))
+        uploaded_file = st.file_uploader("Upload a text file", type=["txt", "csv"]) if data_source == "uploaded file" else None
+        
+        custom_learning_rate = st.slider("Learning Rate", min_value=1e-6, max_value=5e-4, value=3e-5, step=1e-6)
 
+        # Advanced Settings Toggle
+        advanced_toggle = st.checkbox("Advanced Training Settings")
+        if advanced_toggle:
+            warmup_steps = st.slider("Warmup Steps", min_value=0, max_value=500, value=100)
+            weight_decay = st.slider("Weight Decay", min_value=0.0, max_value=0.1, step=0.01, value=0.01)
+        else:
+            warmup_steps = 100
+            weight_decay = 0.01
 
     # Load Dataset
-train_dataset = load_dataset(data_source, tokenizer, uploaded_file=uploaded_file)
-def load_dataset(data_source="demo", tokenizer=None, uploaded_file=None):
-    if data_source == "demo":
-        data = ["Sample text data for model training. This can be replaced with actual data for better performance."]
-    elif uploaded_file is not None:
-        if uploaded_file.name.endswith(".txt"):
-            data = [uploaded_file.read().decode("utf-8")]
-        elif uploaded_file.name.endswith(".csv"):
-            import pandas as pd
-            df = pd.read_csv(uploaded_file)
-            data = df[df.columns[0]].tolist()  # assuming first column is text data
-    else:
-        data = ["No file uploaded. Please upload a dataset."]
-    
-    dataset = prepare_dataset(data, tokenizer)
-    return dataset
-
+    train_dataset = load_dataset(data_source, tokenizer, uploaded_file=uploaded_file)
 
     # Start Training with Progress Bar
     progress_placeholder = st.empty()
@@ -227,3 +215,4 @@ def load_dataset(data_source="demo", tokenizer=None, uploaded_file=None):
 
 if __name__ == "__main__":
     main()
+