use the subfolder param

app.py

@@ -74,35 +74,21 @@ def check_local_model():
 def load_model():
     """Load the model and tokenizer"""
     global model, tokenizer
-    try:
-        if check_local_model():
-            logger.info(f"Loading tokenizer from {LOCAL_MODEL_PATH}")
-            tokenizer = AutoTokenizer.from_pretrained(LOCAL_MODEL_PATH)
-            logger.info(f"Loading int4 model from {LOCAL_MODEL_PATH}")
-            model = AutoModelForCausalLM.from_pretrained(
-                LOCAL_MODEL_PATH,
-                device_map="auto" if DEVICE == "cuda" else "cpu",
-                torch_dtype=torch.bfloat16,
-                trust_remote_code=True
-            )
-        else:
-            logger.info(f"Local model not found, loading from {MAIN_MODEL_ID}")
-            tokenizer = AutoTokenizer.from_pretrained(MAIN_MODEL_ID)
-            logger.info(f"Loading int4 model from {MAIN_MODEL_ID}/int4")
-            model = AutoModelForCausalLM.from_pretrained(
+            # logger.info(f"Loading tokenizer from {LOCAL_MODEL_PATH}")
+    tokenizer = AutoTokenizer.from_pretrained(MAIN_MODEL_ID, subfolder="int4")
+            # logger.info(f"Loading int4 model from {LOCAL_MODEL_PATH}")
+    model = AutoModelForCausalLM.from_pretrained(
                 MAIN_MODEL_ID,
-                subfolder="int4",  # Use the int4 subfolder
+                subfolder="int4",
                 device_map="auto" if DEVICE == "cuda" else "cpu",
                 torch_dtype=torch.bfloat16,
                 trust_remote_code=True
             )
-        if tokenizer.pad_token_id is None:
-            tokenizer.pad_token_id = tokenizer.eos_token_id
+    if tokenizer.pad_token_id is None:
+        tokenizer.pad_token_id = tokenizer.eos_token_id
         logger.info("Model loaded successfully")
         return True
-    except Exception as e:
-        logger.error(f"Error loading model: {e}")
-        return False
+
 
 def create_prompt(system_message, user_message, enable_thinking=True):
     """Create prompt using the model's chat template"""
@@ -193,14 +179,23 @@ def generate_response(message, history, system_message, max_tokens, temperature,
 
 def user(user_message, history):
     """Add user message to history"""
-    return "", history + [[user_message, None]]
+    if history is None:
+        history = []
+    return "", history + [{"role": "user", "content": user_message}]
 
 def bot(history, system_prompt, max_length, temperature, top_p, advanced_checkbox, enable_thinking):
     """Generate bot response"""
-    user_message = history[-1][0]
+    # Get the last user message
+    if not history:
+        return history
+    
+    user_message = history[-1]["content"] if history else ""
+    
     do_sample = advanced_checkbox
     bot_message = generate_response(user_message, history, system_prompt, max_length, temperature, top_p, do_sample, enable_thinking)
-    history[-1][1] = bot_message
+    
+    # Add assistant response to history
+    history.append({"role": "assistant", "content": bot_message})
     return history
 
 # Load model on startup
@@ -268,7 +263,7 @@ with gr.Blocks() as demo:
             generate_button = gr.Button(value="🤖 Petite Elle L'Aime 3")
 
         with gr.Column(scale=2):
-            chatbot = gr.Chatbot(label="🤖 Petite Elle L'Aime 3", type="messages")
+            chatbot = gr.Chatbot(label="🤖 Petite Elle L'Aime 3", type="messages", value=[])
     
     generate_button.click(
         user,
@@ -288,49 +283,49 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    # Advanced model download and verification
-    logger.info("Starting advanced model download and verification process...")
-    try:
-        from download_model import main as download_main, check_model_files, verify_model_integrity
+    # # Advanced model download and verification
+    # logger.info("Starting advanced model download and verification process...")
+    # try:
+    #     from download_model import main as download_main, check_model_files, verify_model_integrity
         
-        # Check if model files already exist and are valid
-        if check_model_files():
-            logger.info("Model files found, verifying integrity...")
-            if verify_model_integrity():
-                logger.info("✅ Model files verified successfully - no download needed")
-            else:
-                logger.warning("⚠️ Model files exist but failed integrity check, re-downloading...")
-                download_success = download_main()
-                if not download_success:
-                    logger.error("❌ Model download failed")
-                    sys.exit(1)
-        else:
-            logger.info("📥 Model files not found, downloading...")
-            download_success = download_main()
-            if download_success:
-                logger.info("✅ Model download and verification completed successfully")
-            else:
-                logger.error("❌ Model download failed")
-                sys.exit(1)
+    #     # Check if model files already exist and are valid
+    #     if check_model_files():
+    #         logger.info("Model files found, verifying integrity...")
+    #         if verify_model_integrity():
+    #             logger.info("✅ Model files verified successfully - no download needed")
+    #         else:
+    #             logger.warning("⚠️ Model files exist but failed integrity check, re-downloading...")
+    #             download_success = download_main()
+    #             if not download_success:
+    #                 logger.error("❌ Model download failed")
+    #                 sys.exit(1)
+    #     else:
+    #         logger.info("📥 Model files not found, downloading...")
+    #         download_success = download_main()
+    #         if download_success:
+    #             logger.info("✅ Model download and verification completed successfully")
+    #         else:
+    #             logger.error("❌ Model download failed")
+    #             sys.exit(1)
                 
-    except ImportError as e:
-        logger.error(f"❌ Error importing download_model: {e}")
-        logger.info("🔄 Continuing with direct model loading...")
-    except Exception as e:
-        logger.error(f"❌ Error during model download process: {e}")
-        logger.info("🔄 Continuing with direct model loading...")
+    # except ImportError as e:
+    #     logger.error(f"❌ Error importing download_model: {e}")
+    #     logger.info("🔄 Continuing with direct model loading...")
+    # except Exception as e:
+    #     logger.error(f"❌ Error during model download process: {e}")
+    #     logger.info("🔄 Continuing with direct model loading...")
     
-    # Load model with enhanced error handling
-    logger.info("🔄 Loading model...")
-    try:
-        if not load_model():
-            logger.error("❌ Failed to load model. Please check the logs above.")
-            sys.exit(1)
-        logger.info("✅ Model loaded successfully")
-    except Exception as e:
-        logger.error(f"❌ Error loading model: {e}")
-        sys.exit(1)
+    # # Load model with enhanced error handling
+    # logger.info("🔄 Loading model...")
+    # try:
+    #     if not load_model():
+    #         logger.error("❌ Failed to load model. Please check the logs above.")
+    #         sys.exit(1)
+    #     logger.info("✅ Model loaded successfully")
+    # except Exception as e:
+    #     logger.error(f"❌ Error loading model: {e}")
+    #     sys.exit(1)
     
-    logger.info("🚀 Starting Gradio application...")
+    # logger.info("🚀 Starting Gradio application...")
     demo.queue()
     demo.launch(ssr_mode=False, mcp_server=True)

download_model.py

@@ -28,8 +28,12 @@ def download_model():
         # Use huggingface_hub to download the model files
         from huggingface_hub import hf_hub_download, list_repo_files
         
-        # List files in the int4 subfolder
-        files = list_repo_files(MAIN_MODEL_ID, subfolder="int4")
+        # List all files in the repository
+        all_files = list_repo_files(MAIN_MODEL_ID)
+        
+        # Filter files that are in the int4 subfolder
+        int4_files = [f for f in all_files if f.startswith("int4/")]
+        logger.info(f"Found {len(int4_files)} files in int4 subfolder")
         
         # Download each required file
         required_files = [
@@ -41,19 +45,23 @@ def download_model():
             "generation_config.json"
         ]
         
+        downloaded_count = 0
         for file_name in required_files:
-            if file_name in files:
+            int4_file_path = f"int4/{file_name}"
+            if int4_file_path in all_files:
                 logger.info(f"Downloading {file_name}...")
                 hf_hub_download(
                     repo_id=MAIN_MODEL_ID,
-                    filename=f"int4/{file_name}",
+                    filename=int4_file_path,
                     local_dir=LOCAL_MODEL_PATH,
                     local_dir_use_symlinks=False
                 )
                 logger.info(f"Downloaded {file_name}")
+                downloaded_count += 1
             else:
                 logger.warning(f"File {file_name} not found in int4 subfolder")
         
+        logger.info(f"Downloaded {downloaded_count} out of {len(required_files)} required files")
         logger.info(f"Model downloaded successfully to {LOCAL_MODEL_PATH}")
         return True
         

verify_spaces_config.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""
+Script to verify Hugging Face Spaces configuration
+"""
+
+import os
+import sys
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def check_required_files():
+    """Check if all required files for HF Spaces deployment exist"""
+    required_files = [
+        "app.py",
+        "requirements.txt", 
+        "README.md",
+        "build.py",
+        "download_model.py",
+        ".gitignore"
+    ]
+    
+    missing_files = []
+    for file in required_files:
+        if not os.path.exists(file):
+            missing_files.append(file)
+    
+    if missing_files:
+        logger.error(f"Missing required files: {missing_files}")
+        return False
+    
+    logger.info("✅ All required files present")
+    return True
+
+def check_app_imports():
+    """Check if app.py can be imported without errors"""
+    try:
+        # Test basic imports
+        import gradio as gr
+        import torch
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+        
+        logger.info("✅ Basic imports successful")
+        return True
+    except Exception as e:
+        logger.error(f"❌ Import error: {e}")
+        return False
+
+def check_download_script():
+    """Check if download script can be imported"""
+    try:
+        from download_model import main as download_main
+        logger.info("✅ Download script import successful")
+        return True
+    except Exception as e:
+        logger.error(f"❌ Download script import error: {e}")
+        return False
+
+def main():
+    """Main verification function"""
+    logger.info("🔍 Verifying Hugging Face Spaces configuration...")
+    
+    checks = [
+        ("Required Files", check_required_files),
+        ("App Imports", check_app_imports),
+        ("Download Script", check_download_script)
+    ]
+    
+    all_passed = True
+    for check_name, check_func in checks:
+        logger.info(f"Checking {check_name}...")
+        if check_func():
+            logger.info(f"✅ {check_name} passed")
+        else:
+            logger.error(f"❌ {check_name} failed")
+            all_passed = False
+    
+    if all_passed:
+        logger.info("🎉 All checks passed! Ready for Hugging Face Spaces deployment.")
+    else:
+        logger.error("❌ Some checks failed. Please fix the issues above.")
+    
+    return all_passed
+
+if __name__ == "__main__":
+    success = main()
+    sys.exit(0 if success else 1)