Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,115 @@
+import gradio as gr
+import os
+import json
+import torch
+from dotenv import load_dotenv
+import logging
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.StreamHandler(),
+        logging.FileHandler("app.log")
+    ]
+)
+logger = logging.getLogger(__name__)
+
+# Load environment variables
+load_dotenv()
+
+# Load config file
+def load_config(config_path="transformers_config.json"):
+    try:
+        with open(config_path, 'r') as f:
+            config = json.load(f)
+        return config
+    except Exception as e:
+        logger.error(f"Error loading config: {str(e)}")
+        return {}
+
+# Load configuration
+config = load_config()
+model_config = config.get("model_config", {})
+
+# Model details from config
+MODEL_NAME = model_config.get("model_name_or_path", "unsloth/DeepSeek-R1-Distill-Qwen-14B-bnb-4bit")
+SPACE_NAME = os.getenv("HF_SPACE_NAME", "phi4training")
+TRAINING_ACTIVE = os.path.exists("TRAINING_ACTIVE")
+
+# Create Gradio interface - training status only, no model outputs
+with gr.Blocks(css="footer {visibility: hidden}") as demo:
+    gr.Markdown(f"# {SPACE_NAME}: Training Status Dashboard")
+    
+    with gr.Row():
+        with gr.Column():
+            status = gr.Markdown(
+                f"""
+                ## Research Training Phase Active
+                
+                **Model**: {MODEL_NAME}
+                **Dataset**: phi4-cognitive-dataset
+                
+                This is a multidisciplinary research training phase. The model is not available for interactive use.
+                
+                ### Training Configuration:
+                - **Epochs**: {config.get("training_config", {}).get("num_train_epochs", 3)}
+                - **Batch Size**: {config.get("training_config", {}).get("per_device_train_batch_size", 2)}
+                - **Gradient Accumulation Steps**: {config.get("training_config", {}).get("gradient_accumulation_steps", 4)}
+                - **Learning Rate**: {config.get("training_config", {}).get("learning_rate", 2e-5)}
+                - **Max Sequence Length**: {config.get("training_config", {}).get("max_seq_length", 2048)}
+                
+                ### Training Status:
+                {"🟢 Training in progress" if TRAINING_ACTIVE else "⚪ Training not currently active"}
+                
+                ⚠️ **NOTE**: This space does not provide model outputs during the research training phase.
+                """
+            )
+    
+    # Add a refresh button to check status
+    refresh_btn = gr.Button("Refresh Status")
+    
+    def refresh_status():
+        # Re-check if training is active
+        training_active = os.path.exists("TRAINING_ACTIVE")
+        return f"""
+        ## Research Training Phase Active
+        
+        **Model**: {MODEL_NAME}
+        **Dataset**: phi4-cognitive-dataset
+        
+        This is a multidisciplinary research training phase. The model is not available for interactive use.
+        
+        ### Training Configuration:
+        - **Epochs**: {config.get("training_config", {}).get("num_train_epochs", 3)}
+        - **Batch Size**: {config.get("training_config", {}).get("per_device_train_batch_size", 2)}
+        - **Gradient Accumulation Steps**: {config.get("training_config", {}).get("gradient_accumulation_steps", 4)}
+        - **Learning Rate**: {config.get("training_config", {}).get("learning_rate", 2e-5)}
+        - **Max Sequence Length**: {config.get("training_config", {}).get("max_seq_length", 2048)}
+        
+        ### Training Status:
+        {"🟢 Training in progress" if training_active else "⚪ Training not currently active"}
+        
+        ⚠️ **NOTE**: This space does not provide model outputs during the research training phase.
+        """
+    
+    refresh_btn.click(refresh_status, outputs=status)
+    
+    gr.Markdown("""
+    ### Research Training Information
+    This model is being fine-tuned on research-focused datasets and is not available for interactive querying.
+    Training logs are available to authorized researchers only.
+    """)
+
+# Launch the interface
+if __name__ == "__main__":
+    # Create an empty TRAINING_ACTIVE file to indicate training is in progress
+    # This would be managed by the actual training script
+    if not os.path.exists("TRAINING_ACTIVE"):
+        with open("TRAINING_ACTIVE", "w") as f:
+            f.write("Training in progress")
+    
+    # Start Gradio with minimal features
+    logger.info("Starting training status dashboard")
+    demo.launch(share=False)