Upload PatentBERT_conversion.ipynb

PatentBERT_conversion.ipynb

@@ -0,0 +1,1193 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 🔄 TensorFlow → PyTorch Conversion\n",
+    "\n",
+    "This section guides you through converting the PatentBERT model from TensorFlow to PyTorch and uploading it to Hugging Face Hub.\n",
+    "\n",
+    "## 📋 Conversion Plan:\n",
+    "\n",
+    "1. **TensorFlow Model Download** (previous cells)\n",
+    "2. **Weight Extraction** - Extract parameters from TensorFlow checkpoint\n",
+    "3. **PyTorch Conversion** - Create equivalent PyTorch model\n",
+    "4. **Model Testing** - Verify that the conversion works\n",
+    "5. **Hugging Face Upload** - Publish to Hub for public use\n",
+    "\n",
+    "## ⚠️ Prerequisites:\n",
+    "- PatentBERT model downloaded (run previous cells first)\n",
+    "- Python 3.7+ with TensorFlow 1.15\n",
+    "- Separate environment with PyTorch to avoid conflicts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🔍 Environment verification...\n",
+      "Python: 3.7.16 (default, Jan 17 2023, 22:20:44) \n",
+      "[GCC 11.2.0]\n",
+      "TensorFlow: 1.15.0\n",
+      "NumPy: 1.21.5\n",
+      "\n",
+      "📂 Checking model files in ./:\n",
+      "✅ model.ckpt-181172.data-00000-of-00001\n",
+      "✅ model.ckpt-181172.index\n",
+      "✅ model.ckpt-181172.meta\n",
+      "✅ bert_config.json\n",
+      "✅ vocab.txt\n",
+      "\n",
+      "✅ All model files are present!\n",
+      "📁 Created: /tmp/patentbert_conversion\n",
+      "📁 Created: /tmp/patentbert_conversion/tf_weights\n",
+      "📁 Created: /tmp/patentbert_conversion/pytorch_model\n",
+      "\n",
+      "🎯 Ready for conversion!\n",
+      "📊 Working directories configured\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Step 1: Environment verification and preparation\n",
+    "\n",
+    "import os\n",
+    "import sys\n",
+    "import json\n",
+    "import numpy as np\n",
+    "import tensorflow as tf\n",
+    "\n",
+    "print(\"🔍 Environment verification...\")\n",
+    "print(f\"Python: {sys.version}\")\n",
+    "print(f\"TensorFlow: {tf.__version__}\")\n",
+    "print(f\"NumPy: {np.__version__}\")\n",
+    "\n",
+    "# Verify that PatentBERT model has been downloaded\n",
+    "model_folder = './'\n",
+    "required_files = [\n",
+    "    'model.ckpt-181172.data-00000-of-00001',\n",
+    "    'model.ckpt-181172.index',\n",
+    "    'model.ckpt-181172.meta',\n",
+    "    'bert_config.json',\n",
+    "    'vocab.txt'\n",
+    "]\n",
+    "\n",
+    "print(f\"\\n📂 Checking model files in {model_folder}:\")\n",
+    "missing_files = []\n",
+    "for file in required_files:\n",
+    "    filepath = os.path.join(model_folder, file)\n",
+    "    if os.path.exists(filepath):\n",
+    "        print(f\"✅ {file}\")\n",
+    "    else:\n",
+    "        print(f\"❌ {file} - MISSING\")\n",
+    "        missing_files.append(file)\n",
+    "\n",
+    "if missing_files:\n",
+    "    print(f\"\\n⚠️  Missing files: {missing_files}\")\n",
+    "    print(\"💡 Please run the previous cells first to download the model\")\n",
+    "else:\n",
+    "    print(\"\\n✅ All model files are present!\")\n",
+    "\n",
+    "# Create working directories for conversion\n",
+    "conversion_dir = \"/tmp/patentbert_conversion\"\n",
+    "tf_weights_dir = os.path.join(conversion_dir, \"tf_weights\")\n",
+    "pytorch_dir = os.path.join(conversion_dir, \"pytorch_model\")\n",
+    "\n",
+    "for dir_path in [conversion_dir, tf_weights_dir, pytorch_dir]:\n",
+    "    os.makedirs(dir_path, exist_ok=True)\n",
+    "    print(f\"📁 Created: {dir_path}\")\n",
+    "\n",
+    "print(f\"\\n🎯 Ready for conversion!\")\n",
+    "print(f\"📊 Working directories configured\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🔄 Extracting weights from TensorFlow PatentBERT model...\n",
+      "📖 Model configuration:\n",
+      "  • Hidden size: 768\n",
+      "  • Number of layers: 12\n",
+      "  • Attention heads: 12\n",
+      "  • Vocabulary size: 30522\n",
+      "🔍 Found 604 variables in checkpoint\n",
+      "📊 176 important variables to extract\n",
+      "🔄 Extraction in progress...\n",
+      "  Progress: 20/176 (11.4%)\n",
+      "  Progress: 20/176 (11.4%)\n",
+      "  Progress: 40/176 (22.7%)\n",
+      "  Progress: 40/176 (22.7%)\n",
+      "  Progress: 60/176 (34.1%)\n",
+      "  Progress: 60/176 (34.1%)\n",
+      "  Progress: 80/176 (45.5%)\n",
+      "  Progress: 80/176 (45.5%)\n",
+      "  Progress: 100/176 (56.8%)\n",
+      "  Progress: 100/176 (56.8%)\n",
+      "  Progress: 120/176 (68.2%)\n",
+      "  Progress: 120/176 (68.2%)\n",
+      "  Progress: 140/176 (79.5%)\n",
+      "  Progress: 140/176 (79.5%)\n",
+      "  Progress: 160/176 (90.9%)\n",
+      "  Progress: 160/176 (90.9%)\n",
+      "  Progress: 176/176 (100.0%)\n",
+      "✅ Extraction completed!\n",
+      "📁 Weights saved in: /tmp/patentbert_conversion/tf_weights\n",
+      "📊 176 weights extracted\n",
+      "💾 Total size: 419.5 MB\n",
+      "\n",
+      "📂 Examples of created files:\n",
+      "  • bert_config.json\n",
+      "  • bert_embeddings_LayerNorm_gamma.npy\n",
+      "  • bert_embeddings_position_embeddings.npy\n",
+      "  • bert_embeddings_token_type_embeddings.npy\n",
+      "  • bert_embeddings_word_embeddings.npy\n",
+      "  ... and 174 other files\n",
+      "\n",
+      "🎉 Extraction successful!\n",
+      "  Progress: 176/176 (100.0%)\n",
+      "✅ Extraction completed!\n",
+      "📁 Weights saved in: /tmp/patentbert_conversion/tf_weights\n",
+      "📊 176 weights extracted\n",
+      "💾 Total size: 419.5 MB\n",
+      "\n",
+      "📂 Examples of created files:\n",
+      "  • bert_config.json\n",
+      "  • bert_embeddings_LayerNorm_gamma.npy\n",
+      "  • bert_embeddings_position_embeddings.npy\n",
+      "  • bert_embeddings_token_type_embeddings.npy\n",
+      "  • bert_embeddings_word_embeddings.npy\n",
+      "  ... and 174 other files\n",
+      "\n",
+      "🎉 Extraction successful!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Step 2: TensorFlow model weights extraction\n",
+    "\n",
+    "print(\"🔄 Extracting weights from TensorFlow PatentBERT model...\")\n",
+    "\n",
+    "def extract_tf_weights():\n",
+    "    \"\"\"Extract all weights from TensorFlow checkpoint\"\"\"\n",
+    "    \n",
+    "    # File paths\n",
+    "    checkpoint_path = \"./model.ckpt-181172\"\n",
+    "    config_path = \"./bert_config.json\"\n",
+    "    vocab_path = \"./vocab.txt\"\n",
+    "    \n",
+    "    # Read BERT configuration\n",
+    "    with open(config_path, 'r') as f:\n",
+    "        config = json.load(f)\n",
+    "    \n",
+    "    print(f\"📖 Model configuration:\")\n",
+    "    print(f\"  • Hidden size: {config.get('hidden_size', 768)}\")\n",
+    "    print(f\"  • Number of layers: {config.get('num_hidden_layers', 12)}\")\n",
+    "    print(f\"  • Attention heads: {config.get('num_attention_heads', 12)}\")\n",
+    "    print(f\"  • Vocabulary size: {config.get('vocab_size', 30522)}\")\n",
+    "    \n",
+    "    # List all variables in checkpoint\n",
+    "    var_list = tf.train.list_variables(checkpoint_path)\n",
+    "    print(f\"🔍 Found {len(var_list)} variables in checkpoint\")\n",
+    "    \n",
+    "    # Filter important variables (ignore optimization variables)\n",
+    "    skip_patterns = ['adam', 'beta', 'global_step', 'learning_rate']\n",
+    "    important_vars = []\n",
+    "    \n",
+    "    for name, shape in var_list:\n",
+    "        if not any(pattern in name.lower() for pattern in skip_patterns):\n",
+    "            important_vars.append((name, shape))\n",
+    "    \n",
+    "    print(f\"📊 {len(important_vars)} important variables to extract\")\n",
+    "    \n",
+    "    # Extract and save weights\n",
+    "    weights_info = {}\n",
+    "    total_size = 0\n",
+    "    \n",
+    "    print(\"🔄 Extraction in progress...\")\n",
+    "    for i, (name, shape) in enumerate(important_vars):\n",
+    "        try:\n",
+    "            # Load variable\n",
+    "            weight = tf.train.load_variable(checkpoint_path, name)\n",
+    "            \n",
+    "            # Create safe filename\n",
+    "            safe_name = name.replace('/', '_').replace(':', '_').replace(' ', '_')\n",
+    "            filename = f\"{safe_name}.npy\"\n",
+    "            \n",
+    "            # Save in NumPy format\n",
+    "            filepath = os.path.join(tf_weights_dir, filename)\n",
+    "            np.save(filepath, weight)\n",
+    "            \n",
+    "            # Record metadata\n",
+    "            weights_info[name] = {\n",
+    "                'filename': filename,\n",
+    "                'shape': list(shape),\n",
+    "                'dtype': str(weight.dtype),\n",
+    "                'size_mb': weight.nbytes / (1024 * 1024)\n",
+    "            }\n",
+    "            \n",
+    "            total_size += weight.nbytes\n",
+    "            \n",
+    "            # Show progress\n",
+    "            if (i + 1) % 20 == 0 or (i + 1) == len(important_vars):\n",
+    "                print(f\"  Progress: {i + 1}/{len(important_vars)} ({(i+1)/len(important_vars)*100:.1f}%)\")\n",
+    "                \n",
+    "        except Exception as e:\n",
+    "            print(f\"⚠️  Error for {name}: {e}\")\n",
+    "            continue\n",
+    "    \n",
+    "    # Create complete metadata\n",
+    "    metadata = {\n",
+    "        'model_info': {\n",
+    "            'name': 'PatentBERT',\n",
+    "            'source': 'TensorFlow',\n",
+    "            'checkpoint_path': checkpoint_path,\n",
+    "            'extraction_date': '2025-07-20'\n",
+    "        },\n",
+    "        'config': config,\n",
+    "        'weights_info': weights_info,\n",
+    "        'statistics': {\n",
+    "            'total_weights': len(weights_info),\n",
+    "            'total_size_mb': total_size / (1024 * 1024),\n",
+    "            'original_variables': len(var_list),\n",
+    "            'extracted_variables': len(weights_info)\n",
+    "        }\n",
+    "    }\n",
+    "    \n",
+    "    # Save metadata\n",
+    "    metadata_path = os.path.join(tf_weights_dir, 'extraction_metadata.json')\n",
+    "    with open(metadata_path, 'w') as f:\n",
+    "        json.dump(metadata, f, indent=2)\n",
+    "    \n",
+    "    # Copy configuration files\n",
+    "    import shutil\n",
+    "    shutil.copy(config_path, os.path.join(tf_weights_dir, 'bert_config.json'))\n",
+    "    shutil.copy(vocab_path, os.path.join(tf_weights_dir, 'vocab.txt'))\n",
+    "    \n",
+    "    print(f\"✅ Extraction completed!\")\n",
+    "    print(f\"📁 Weights saved in: {tf_weights_dir}\")\n",
+    "    print(f\"📊 {len(weights_info)} weights extracted\")\n",
+    "    print(f\"💾 Total size: {total_size / (1024 * 1024):.1f} MB\")\n",
+    "    \n",
+    "    # Show some examples of extracted weights\n",
+    "    print(f\"\\n📂 Examples of created files:\")\n",
+    "    files = sorted(os.listdir(tf_weights_dir))\n",
+    "    for i, file in enumerate(files[:5]):\n",
+    "        print(f\"  • {file}\")\n",
+    "    if len(files) > 5:\n",
+    "        print(f\"  ... and {len(files) - 5} other files\")\n",
+    "    \n",
+    "    return tf_weights_dir, metadata\n",
+    "\n",
+    "# Execute extraction\n",
+    "try:\n",
+    "    weights_dir, metadata = extract_tf_weights()\n",
+    "    print(\"\\n🎉 Extraction successful!\")\n",
+    "    \n",
+    "except Exception as e:\n",
+    "    print(f\"❌ Error during extraction: {e}\")\n",
+    "    import traceback\n",
+    "    traceback.print_exc()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🎯 Converting TensorFlow weights to PyTorch format...\n",
+      "✅ CORRECTED upload script created!\n",
+      "\n",
+      "🔧 Key corrections:\n",
+      "   ✅ Accepts BOTH model.safetensors AND pytorch_model.bin\n",
+      "   ✅ Automatically detects model format\n",
+      "   ✅ Improved error messages\n",
+      "   ✅ Better commit message with format info\n",
+      "   ✅ Proper torch import for testing\n",
+      "\n",
+      "🚀 NOW RUN THIS CORRECTED COMMAND:\n",
+      "   python /tmp/upload_to_hf.py patentbert_conversion/pytorch_model ZoeYou/patentbert-pytorch xxxxx\n",
+      "\n",
+      "💡 Or use the new corrected script:\n",
+      "   python /tmp/upload_to_hf_corrected.py patentbert_conversion/pytorch_model ZoeYou/patentbert-pytorch xxxxx\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Step 3: Convert TensorFlow weights to PyTorch format\n",
+    "\n",
+    "print(\"🎯 Converting TensorFlow weights to PyTorch format...\")\n",
+    "\n",
+    "corrected_upload_script = \"\"\"#!/usr/bin/env python3\n",
+    "import os\n",
+    "import sys\n",
+    "from huggingface_hub import HfApi, create_repo, upload_folder\n",
+    "from transformers import BertForSequenceClassification, BertTokenizer\n",
+    "\n",
+    "def check_model_files(model_dir):\n",
+    "    \\\"\\\"\\\"Check for required model files with support for both formats.\\\"\\\"\\\"\n",
+    "    \n",
+    "    # Required base files\n",
+    "    required_base = ['config.json', 'vocab.txt', 'tokenizer_config.json']\n",
+    "    \n",
+    "    # Model files (at least one of these)\n",
+    "    model_files = ['model.safetensors', 'pytorch_model.bin']\n",
+    "    \n",
+    "    missing_base = []\n",
+    "    for file in required_base:\n",
+    "        if not os.path.exists(os.path.join(model_dir, file)):\n",
+    "            missing_base.append(file)\n",
+    "    \n",
+    "    # Check for at least one model file\n",
+    "    found_model_files = []\n",
+    "    for f in model_files:\n",
+    "        if os.path.exists(os.path.join(model_dir, f)):\n",
+    "            found_model_files.append(f)\n",
+    "    \n",
+    "    if missing_base:\n",
+    "        print(f\"❌ Missing required files: {missing_base}\")\n",
+    "        return False\n",
+    "    \n",
+    "    if not found_model_files:\n",
+    "        print(f\"❌ No model file found. Expected one of: {model_files}\")\n",
+    "        return False\n",
+    "    \n",
+    "    # Show found files\n",
+    "    all_files = os.listdir(model_dir)\n",
+    "    print(f\"✅ Model files found: {all_files}\")\n",
+    "    print(f\"✅ Model weights format: {found_model_files[0]}\")\n",
+    "    return True\n",
+    "\n",
+    "def test_model_loading(model_dir):\n",
+    "    \\\"\\\"\\\"Test model loading to verify it works.\\\"\\\"\\\"\n",
+    "    try:\n",
+    "        print(\"🧪 Model loading test...\")\n",
+    "        \n",
+    "        # Load model and tokenizer\n",
+    "        model = BertForSequenceClassification.from_pretrained(model_dir)\n",
+    "        tokenizer = BertTokenizer.from_pretrained(model_dir)\n",
+    "        \n",
+    "        print(f\"✅ Model loaded: {model.config.num_labels} classes, {model.config.hidden_size} hidden\")\n",
+    "        print(f\"✅ Tokenizer loaded: {len(tokenizer)} tokens\")\n",
+    "        \n",
+    "        # Quick inference test\n",
+    "        text = \"A method for producing synthetic materials\"\n",
+    "        inputs = tokenizer(text, return_tensors=\"pt\", max_length=512, truncation=True, padding=True)\n",
+    "        \n",
+    "        import torch\n",
+    "        with torch.no_grad():\n",
+    "            outputs = model(**inputs)\n",
+    "            predictions = outputs.logits.softmax(dim=-1)\n",
+    "        \n",
+    "        print(f\"✅ Inference test successful: shape {predictions.shape}\")\n",
+    "        return True\n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(f\"❌ Test error: {e}\")\n",
+    "        return False\n",
+    "\n",
+    "def upload_to_huggingface(model_dir, repo_name, token, private=False):\n",
+    "    \\\"\\\"\\\"Upload model to Hugging Face Hub with support for all formats.\\\"\\\"\\\"\n",
+    "    \n",
+    "    print(\"🚀 Upload to Hugging Face Hub\")\n",
+    "    print(f\"📂 Model: {model_dir}\")\n",
+    "    print(f\"🏷️  Repository: {repo_name}\")\n",
+    "    print(f\"🔒 Private: {private}\")\n",
+    "    \n",
+    "    # File verification\n",
+    "    if not check_model_files(model_dir):\n",
+    "        return False\n",
+    "    \n",
+    "    # Loading test\n",
+    "    if not test_model_loading(model_dir):\n",
+    "        print(\"⚠️  Warning: Model doesn't load correctly, but continuing upload...\")\n",
+    "    \n",
+    "    try:\n",
+    "        # Initialize API\n",
+    "        api = HfApi(token=token)\n",
+    "        \n",
+    "        # Check connection\n",
+    "        user_info = api.whoami()\n",
+    "        print(f\"✅ Connected as: {user_info['name']}\")\n",
+    "        \n",
+    "        # Create or verify repository\n",
+    "        try:\n",
+    "            create_repo(repo_name, token=token, private=private, exist_ok=True)\n",
+    "            print(f\"✅ Repository created/verified: https://huggingface.co/{repo_name}\")\n",
+    "        except Exception as e:\n",
+    "            print(f\"⚠️  Repository warning: {e}\")\n",
+    "        \n",
+    "        # Upload complete folder\n",
+    "        print(\"📤 Uploading files...\")\n",
+    "        \n",
+    "        # Determine model format\n",
+    "        model_format = \"SafeTensors\" if os.path.exists(os.path.join(model_dir, 'model.safetensors')) else \"PyTorch\"\n",
+    "        \n",
+    "        # Create informative commit message\n",
+    "        commit_message = f\\\"\\\"\\\"Upload PatentBERT PyTorch model\n",
+    "\n",
+    "BERT model fine-tuned for patent classification, converted from TensorFlow to PyTorch.\n",
+    "\n",
+    "Specifications:\n",
+    "- Format: {model_format}\n",
+    "- Classes: Auto-detected from config.json  \n",
+    "- Conversion: TensorFlow 1.15 → PyTorch via transformers\n",
+    "- CPC Labels: Real Cooperative Patent Classification labels included\n",
+    "\n",
+    "Included files:\n",
+    "{', '.join(sorted(os.listdir(model_dir)))}\n",
+    "\\\"\\\"\\\"\n",
+    "        \n",
+    "        upload_folder(\n",
+    "            folder_path=model_dir,\n",
+    "            repo_id=repo_name,\n",
+    "            token=token,\n",
+    "            commit_message=commit_message,\n",
+    "            ignore_patterns=[\".git\", \".gitattributes\", \"*.tmp\"]\n",
+    "        )\n",
+    "        \n",
+    "        print(\"🎉 Upload completed successfully!\")\n",
+    "        print(f\"🌐 Model available at: https://huggingface.co/{repo_name}\")\n",
+    "        \n",
+    "        # Usage instructions\n",
+    "        print(\"\\\\n📋 Usage instructions:\")\n",
+    "        print(f\"from transformers import BertForSequenceClassification, BertTokenizer\")\n",
+    "        print(f\"model = BertForSequenceClassification.from_pretrained('{repo_name}')\")\n",
+    "        print(f\"tokenizer = BertTokenizer.from_pretrained('{repo_name}')\")\n",
+    "        \n",
+    "        return True\n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(f\"❌ Upload error: {e}\")\n",
+    "        import traceback\n",
+    "        traceback.print_exc()\n",
+    "        return False\n",
+    "\n",
+    "def main():\n",
+    "    if len(sys.argv) != 4:\n",
+    "        print(\"Usage: python upload_to_hf.py <model_dir> <repo_name> <hf_token>\")\n",
+    "        print(\"Example: python upload_to_hf.py ./pytorch_model ZoeYou/patentbert-pytorch hf_xxx...\")\n",
+    "        sys.exit(1)\n",
+    "    \n",
+    "    model_dir = sys.argv[1]\n",
+    "    repo_name = sys.argv[2]\n",
+    "    token = sys.argv[3]\n",
+    "    \n",
+    "    if not os.path.exists(model_dir):\n",
+    "        print(f\"❌ Directory not found: {model_dir}\")\n",
+    "        sys.exit(1)\n",
+    "    \n",
+    "    success = upload_to_huggingface(model_dir, repo_name, token, private=False)\n",
+    "    \n",
+    "    if success:\n",
+    "        print(\"\\\\n✅ UPLOAD SUCCESSFUL!\")\n",
+    "    else:\n",
+    "        print(\"\\\\n❌ UPLOAD FAILED!\")\n",
+    "        sys.exit(1)\n",
+    "\n",
+    "if __name__ == \"__main__\":\n",
+    "    # Import torch for loading test\n",
+    "    try:\n",
+    "        import torch\n",
+    "    except ImportError:\n",
+    "        print(\"⚠️  torch not available, loading test skipped\")\n",
+    "        \n",
+    "    main()\n",
+    "\"\"\"\n",
+    "\n",
+    "# Save the corrected upload script\n",
+    "with open('/tmp/upload_to_hf_corrected.py', 'w', encoding='utf-8') as f:\n",
+    "    f.write(corrected_upload_script)\n",
+    "\n",
+    "# Also overwrite the original script\n",
+    "with open('/tmp/upload_to_hf.py', 'w', encoding='utf-8') as f:\n",
+    "    f.write(corrected_upload_script)\n",
+    "\n",
+    "print(\"✅ CORRECTED upload script created!\")\n",
+    "print(\"\\n🔧 Key corrections:\")\n",
+    "print(\"   ✅ Accepts BOTH model.safetensors AND pytorch_model.bin\")\n",
+    "print(\"   ✅ Automatically detects model format\")\n",
+    "print(\"   ✅ Improved error messages\")\n",
+    "print(\"   ✅ Better commit message with format info\")\n",
+    "print(\"   ✅ Proper torch import for testing\")\n",
+    "\n",
+    "print(\"\\n🚀 NOW RUN THIS CORRECTED COMMAND:\")\n",
+    "print(\"   python /tmp/upload_to_hf.py patentbert_conversion/pytorch_model ZoeYou/patentbert-pytorch xxxxx\")\n",
+    "\n",
+    "print(\"\\n💡 Or use the new corrected script:\")\n",
+    "print(\"   python /tmp/upload_to_hf_corrected.py patentbert_conversion/pytorch_model ZoeYou/patentbert-pytorch xxxxx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 🎉 UPLOAD SUCCESS! Let's test the uploaded model\n",
+    "\n",
+    "print(\"🎉 Upload successful! Testing the uploaded model from Hugging Face...\")\n",
+    "\n",
+    "# Test the uploaded model\n",
+    "\n",
+    "from transformers import BertForSequenceClassification, BertTokenizer\n",
+    "import torch\n",
+    "\n",
+    "print(\"🔍 Testing uploaded PatentBERT model from Hugging Face...\")\n",
+    "\n",
+    "try:\n",
+    "    # Load model and tokenizer from Hugging Face Hub\n",
+    "    model = BertForSequenceClassification.from_pretrained('ZoeYou/patentbert-pytorch')\n",
+    "    tokenizer = BertTokenizer.from_pretrained('ZoeYou/patentbert-pytorch')\n",
+    "    \n",
+    "    print(f\"✅ Model loaded: {model.config.num_labels} classes\")\n",
+    "    print(f\"✅ Tokenizer loaded: {len(tokenizer)} tokens\")\n",
+    "    \n",
+    "    # Test inference\n",
+    "    text = \"A method for producing synthetic materials with enhanced properties\"\n",
+    "    inputs = tokenizer(text, return_tensors=\"pt\", max_length=512, truncation=True, padding=True)\n",
+    "    \n",
+    "    with torch.no_grad():\n",
+    "        outputs = model(**inputs)\n",
+    "        predictions = outputs.logits.softmax(dim=-1)\n",
+    "    \n",
+    "    # Get top prediction\n",
+    "    predicted_class_id = predictions.argmax().item()\n",
+    "    confidence = predictions.max().item()\n",
+    "    \n",
+    "    # Use real CPC labels if available\n",
+    "    if hasattr(model.config, 'id2label') and model.config.id2label:\n",
+    "        predicted_label = model.config.id2label[predicted_class_id]\n",
+    "        print(f\"✅ Predicted CPC class: {predicted_label} (ID: {predicted_class_id})\")\n",
+    "    else:\n",
+    "        print(f\"✅ Predicted class ID: {predicted_class_id}\")\n",
+    "    \n",
+    "    print(f\"✅ Confidence: {confidence:.2%}\")\n",
+    "    print(\"🎉 Model works perfectly from Hugging Face!\")\n",
+    "    \n",
+    "except Exception as e:\n",
+    "    print(f\"❌ Error: {e}\")\n",
+    "\n",
+    "\n",
+    "print(\"📝 Model test code ready. Your model is now live at:\")\n",
+    "print(\"🌐 https://huggingface.co/ZoeYou/patentbert-pytorch\")\n",
+    "\n",
+    "print(\"\\\\n📋 Quick usage example:\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🎉 CONVERSION SUCCESSFUL! Upload script correction...\n",
+      "✅ CORRECTED upload script created!\n",
+      "\n",
+      "🔧 Applied corrections:\n",
+      "   ✅ Accepts model.safetensors AND pytorch_model.bin\n",
+      "   ✅ Model loading test before upload\n",
+      "   ✅ Robust file verification\n",
+      "   ✅ Informative commit message\n",
+      "   ✅ Usage instructions included\n",
+      "\n",
+      "🚀 CORRECTED COMMAND:\n",
+      "   python upload_to_hf.py patentbert_conversion/pytorch_model ZoeYou/patentbert-pytorch xxxxx\n"
+     ]
+    }
+   ],
+   "source": [
+    "# step 4: Provide usage example for the uploaded model\n",
+    "\n",
+    "# 🎉 CONVERSION SUCCESS! Upload script correction\n",
+    "\n",
+    "print(\"🎉 CONVERSION SUCCESSFUL! Upload script correction...\")\n",
+    "\n",
+    "upload_script = \"\"\"#!/usr/bin/env python3\n",
+    "import os\n",
+    "import sys\n",
+    "from huggingface_hub import HfApi, create_repo, upload_folder\n",
+    "from transformers import BertForSequenceClassification, BertTokenizer\n",
+    "\n",
+    "def check_model_files(model_dir):\n",
+    "    \\\"\\\"\\\"Check for required model files.\\\"\\\"\\\"\n",
+    "    \n",
+    "    # Required base files\n",
+    "    required_base = ['config.json', 'vocab.txt', 'tokenizer_config.json']\n",
+    "    \n",
+    "    # Model files (at least one of these)\n",
+    "    model_files = ['model.safetensors', 'pytorch_model.bin']\n",
+    "    \n",
+    "    missing_base = []\n",
+    "    for file in required_base:\n",
+    "        if not os.path.exists(os.path.join(model_dir, file)):\n",
+    "            missing_base.append(file)\n",
+    "    \n",
+    "    # Check for at least one model file\n",
+    "    has_model_file = any(os.path.exists(os.path.join(model_dir, f)) for f in model_files)\n",
+    "    \n",
+    "    if missing_base:\n",
+    "        print(f\"❌ Missing required files: {missing_base}\")\n",
+    "        return False\n",
+    "    \n",
+    "    if not has_model_file:\n",
+    "        print(f\"❌ No model file found. Expected: {model_files}\")\n",
+    "        return False\n",
+    "    \n",
+    "    # Show found files\n",
+    "    found_files = []\n",
+    "    for file in os.listdir(model_dir):\n",
+    "        if os.path.isfile(os.path.join(model_dir, file)):\n",
+    "            found_files.append(file)\n",
+    "    \n",
+    "    print(f\"✅ Model files found: {found_files}\")\n",
+    "    return True\n",
+    "\n",
+    "def test_model_loading(model_dir):\n",
+    "    \\\"\\\"\\\"Test model loading to verify it works.\\\"\\\"\\\"\n",
+    "    try:\n",
+    "        print(\"🧪 Model loading test...\")\n",
+    "        \n",
+    "        # Load model and tokenizer\n",
+    "        model = BertForSequenceClassification.from_pretrained(model_dir)\n",
+    "        tokenizer = BertTokenizer.from_pretrained(model_dir)\n",
+    "        \n",
+    "        print(f\"✅ Model loaded: {model.config.num_labels} classes, {model.config.hidden_size} hidden\")\n",
+    "        print(f\"✅ Tokenizer loaded: {len(tokenizer)} tokens\")\n",
+    "        \n",
+    "        # Quick inference test\n",
+    "        text = \"A method for producing synthetic materials\"\n",
+    "        inputs = tokenizer(text, return_tensors=\"pt\", max_length=512, truncation=True, padding=True)\n",
+    "        \n",
+    "        with torch.no_grad():\n",
+    "            outputs = model(**inputs)\n",
+    "            predictions = outputs.logits.softmax(dim=-1)\n",
+    "        \n",
+    "        print(f\"✅ Inference test successful: shape {predictions.shape}\")\n",
+    "        return True\n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(f\"❌ Test error: {e}\")\n",
+    "        return False\n",
+    "\n",
+    "def upload_to_huggingface(model_dir, repo_name, token, private=False):\n",
+    "    \\\"\\\"\\\"Upload model to Hugging Face Hub.\\\"\\\"\\\"\n",
+    "    \n",
+    "    print(\"🚀 Upload to Hugging Face Hub\")\n",
+    "    print(f\"📂 Model: {model_dir}\")\n",
+    "    print(f\"🏷️  Repository: {repo_name}\")\n",
+    "    print(f\"🔒 Private: {private}\")\n",
+    "    \n",
+    "    # File verification\n",
+    "    if not check_model_files(model_dir):\n",
+    "        return False\n",
+    "    \n",
+    "    # Loading test\n",
+    "    if not test_model_loading(model_dir):\n",
+    "        print(\"⚠️  Warning: Model doesn't load correctly, but continuing upload...\")\n",
+    "    \n",
+    "    try:\n",
+    "        # Initialize API\n",
+    "        api = HfApi(token=token)\n",
+    "        \n",
+    "        # Check connection\n",
+    "        user_info = api.whoami()\n",
+    "        print(f\"✅ Connected as: {user_info['name']}\")\n",
+    "        \n",
+    "        # Create or verify repository\n",
+    "        try:\n",
+    "            create_repo(repo_name, token=token, private=private, exist_ok=True)\n",
+    "            print(f\"✅ Repository created/verified: https://huggingface.co/{repo_name}\")\n",
+    "        except Exception as e:\n",
+    "            print(f\"⚠️  Repository warning: {e}\")\n",
+    "        \n",
+    "        # Upload complete folder\n",
+    "        print(\"📤 Uploading files...\")\n",
+    "        \n",
+    "        # Create informative commit message\n",
+    "        commit_message = f\\\"\\\"\\\"Upload PatentBERT PyTorch model\n",
+    "\n",
+    "BERT model fine-tuned for patent classification, converted from TensorFlow to PyTorch.\n",
+    "\n",
+    "Specifications:\n",
+    "- Format: {'SafeTensors' if os.path.exists(os.path.join(model_dir, 'model.safetensors')) else 'PyTorch'}\n",
+    "- Classes: Auto-detected from config.json\n",
+    "- Conversion: TensorFlow 1.15 → PyTorch via transformers\n",
+    "\n",
+    "Included files:\n",
+    "{', '.join(os.listdir(model_dir))}\n",
+    "\\\"\\\"\\\"\n",
+    "        \n",
+    "        upload_folder(\n",
+    "            folder_path=model_dir,\n",
+    "            repo_id=repo_name,\n",
+    "            token=token,\n",
+    "            commit_message=commit_message,\n",
+    "            ignore_patterns=[\".git\", \".gitattributes\", \"*.tmp\"]\n",
+    "        )\n",
+    "        \n",
+    "        print(\"🎉 Upload completed successfully!\")\n",
+    "        print(f\"🌐 Model available at: https://huggingface.co/{repo_name}\")\n",
+    "        \n",
+    "        # Usage instructions\n",
+    "        print(\"\\\\n📋 Usage instructions:\")\n",
+    "        print(f\"from transformers import BertForSequenceClassification, BertTokenizer\")\n",
+    "        print(f\"model = BertForSequenceClassification.from_pretrained('{repo_name}')\")\n",
+    "        print(f\"tokenizer = BertTokenizer.from_pretrained('{repo_name}')\")\n",
+    "        \n",
+    "        return True\n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(f\"❌ Upload error: {e}\")\n",
+    "        return False\n",
+    "\n",
+    "def main():\n",
+    "    if len(sys.argv) != 4:\n",
+    "        print(\"Usage: python upload_to_hf.py <model_dir> <repo_name> <hf_token>\")\n",
+    "        print(\"Example: python upload_to_hf.py ./pytorch_model ZoeYou/patentbert-pytorch hf_xxx...\")\n",
+    "        sys.exit(1)\n",
+    "    \n",
+    "    model_dir = sys.argv[1]\n",
+    "    repo_name = sys.argv[2]\n",
+    "    token = sys.argv[3]\n",
+    "    \n",
+    "    if not os.path.exists(model_dir):\n",
+    "        print(f\"❌ Directory not found: {model_dir}\")\n",
+    "        sys.exit(1)\n",
+    "    \n",
+    "    success = upload_to_huggingface(model_dir, repo_name, token, private=False)\n",
+    "    \n",
+    "    if success:\n",
+    "        print(\"\\\\n✅ UPLOAD SUCCESSFUL!\")\n",
+    "    else:\n",
+    "        print(\"\\\\n❌ UPLOAD FAILED!\")\n",
+    "        sys.exit(1)\n",
+    "\n",
+    "if __name__ == \"__main__\":\n",
+    "    # Import torch for loading test\n",
+    "    try:\n",
+    "        import torch\n",
+    "    except ImportError:\n",
+    "        print(\"⚠️  torch not available, loading test skipped\")\n",
+    "        \n",
+    "    main()\n",
+    "\"\"\"\n",
+    "\n",
+    "# Save corrected upload script\n",
+    "with open('/tmp/upload_to_hf.py', 'w', encoding='utf-8') as f:\n",
+    "    f.write(upload_script)\n",
+    "\n",
+    "print(\"✅ CORRECTED upload script created!\")\n",
+    "print(\"\\n🔧 Applied corrections:\")\n",
+    "print(\"   ✅ Accepts model.safetensors AND pytorch_model.bin\")\n",
+    "print(\"   ✅ Model loading test before upload\")\n",
+    "print(\"   ✅ Robust file verification\")\n",
+    "print(\"   ✅ Informative commit message\")\n",
+    "print(\"   ✅ Usage instructions included\")\n",
+    "\n",
+    "print(\"\\n🚀 CORRECTED COMMAND:\")\n",
+    "print(\"   python upload_to_hf.py patentbert_conversion/pytorch_model ZoeYou/patentbert-pytorch xxxxx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "🎯 COMPLETE TENSORFLOW → PYTORCH CONVERSION GUIDE\n",
+    "\n",
+    "📋 4-step process:\n",
+    "\n",
+    "1️⃣  **DOWNLOAD** (in this notebook)\n",
+    "   • Run previous cells to download PatentBERT\n",
+    "   • Model will be in ./\n",
+    "\n",
+    "2️⃣  **EXTRACTION** (in this notebook)\n",
+    "   • Run TensorFlow weight extraction cell\n",
+    "   • Weights will be extracted to /tmp/patentbert_conversion/tf_weights/\n",
+    "\n",
+    "3️⃣  **CONVERSION** (Python 3.8+ environment)\n",
+    "   ```\n",
+    "   bash /tmp/install_pytorch_env.sh\n",
+    "   source patentbert_pytorch/bin/activate\n",
+    "   python /tmp/convert_patentbert.py /tmp/patentbert_conversion/tf_weights /tmp/patentbert_conversion/pytorch_model\n",
+    "   ```\n",
+    "\n",
+    "4️⃣  **TEST AND UPLOAD**\n",
+    "\n",
+    "   `python /tmp/test_patentbert.py /tmp/patentbert_conversion/pytorch_model`\n",
+    "\n",
+    "   `python /tmp/upload_to_hf.py /tmp/patentbert_conversion/pytorch_model username/patentbert-pytorch your_hf_token`\n",
+    "\n",
+    "🎉 RESULT:\n",
+    "• PyTorch model ready for production\n",
+    "• Compatible with Hugging Face Transformers\n",
+    "• Publicly available on Hub\n",
+    "• Documentation and examples included\n",
+    "\n",
+    "💡 TIP:\n",
+    "First create an account at https://huggingface.co/ and get your access token\n",
+    "from https://huggingface.co/settings/tokens\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🏷️ Creating and adding CPC class labels...\n",
+      "✅ Loaded 656 real CPC labels from PatentBERT\n",
+      "📝 Example labels from the real data:\n",
+      "     0: A01B - SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRIC...\n",
+      "    50: A46B - BRUSHES ...\n",
+      "   100: B07B - SEPERATING SOLIDS FROM SOLIDS BY SIEVING, SCREENING, OR SIFTING OR BY USING GAS ...\n",
+      "   200: B60Q - ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREO...\n",
+      "   300: C10F - DRYING OR WORKING-UP OF PEAT...\n",
+      "   400: E04G - SCAFFOLDING; FORMS; SHUTTERING; BUILDING IMPLEMENTS OR OTHER BUILDING AIDS, OR T...\n",
+      "   500: F28B - STEAM OR VAPOUR CONDENSERS ...\n",
+      "   600: H01H - ELECTRIC SWITCHES; RELAYS; SELECTORS...\n",
+      "   655: Y10T - TECHNICAL SUBJECTS COVERED BY FORMER US CLASSIFICATION...\n",
+      "\n",
+      "✅ Real CPC system structure:\n",
+      "   📊 Total classes: 656\n",
+      "   📈 Distribution by section:\n",
+      "      A: 84 classes\n",
+      "      B: 171 classes\n",
+      "      C: 88 classes\n",
+      "      D: 40 classes\n",
+      "      E: 31 classes\n",
+      "      F: 101 classes\n",
+      "      G: 81 classes\n",
+      "      H: 51 classes\n",
+      "      Y: 9 classes\n",
+      "✅ Labels saved to: /tmp/patentbert_conversion/pytorch_model/labels.json\n",
+      "✅ Configuration updated with real CPC labels\n",
+      "✅ README updated with REAL CPC label documentation\n",
+      "\n",
+      "📁 Added/updated files:\n",
+      "   • labels.json - Complete mapping of 656 REAL CPC labels\n",
+      "   • config.json - Updated configuration with authentic id2label/label2id\n",
+      "   • README.md - Complete documentation with real CPC distribution\n",
+      "\n",
+      "🎯 Model is now ready for upload with AUTHENTIC CPC labels!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 🏷️ ADDING CLASS LABELS - Essential for prediction interpretation\n",
+    "\n",
+    "print(\"🏷️ Creating and adding CPC class labels...\")\n",
+    "\n",
+    "# Load the REAL CPC labels from the original PatentBERT label file\n",
+    "import pandas as pd\n",
+    "import json\n",
+    "import os\n",
+    "\n",
+    "# Load the real CPC labels\n",
+    "label_file_path = \"/home/yzuo/scratch/representation_learning/patentmapv1/PatentBert/labels_group_id.tsv\"\n",
+    "cpc_df = pd.read_csv(label_file_path, sep='\\t')\n",
+    "\n",
+    "print(f\"✅ Loaded {len(cpc_df)} real CPC labels from PatentBERT\")\n",
+    "print(f\"📝 Example labels from the real data:\")\n",
+    "for i in [0, 50, 100, 200, 300, 400, 500, 600, 655]:\n",
+    "    if i < len(cpc_df):\n",
+    "        row = cpc_df.iloc[i]\n",
+    "        print(f\"   {i:3d}: {row['id']} - {row['title'][:80]}...\")\n",
+    "\n",
+    "# Extract labels and descriptions\n",
+    "cpc_labels = cpc_df['id'].tolist()\n",
+    "cpc_descriptions = [f\"{row['id']}: {row['title']}\" for _, row in cpc_df.iterrows()]\n",
+    "\n",
+    "print(f\"\\n✅ Real CPC system structure:\")\n",
+    "print(f\"   📊 Total classes: {len(cpc_labels)}\")\n",
+    "\n",
+    "# Analyze the actual distribution by section\n",
+    "section_counts = {}\n",
+    "for label in cpc_labels:\n",
+    "    section = label[0]\n",
+    "    section_counts[section] = section_counts.get(section, 0) + 1\n",
+    "\n",
+    "print(f\"   📈 Distribution by section:\")\n",
+    "for section, count in sorted(section_counts.items()):\n",
+    "    print(f\"      {section}: {count} classes\")\n",
+    "\n",
+    "# Create label configuration file\n",
+    "label_config = {\n",
+    "    \"id2label\": {str(i): label for i, label in enumerate(cpc_labels)},\n",
+    "    \"label2id\": {label: i for i, label in enumerate(cpc_labels)},\n",
+    "    \"num_labels\": len(cpc_labels),\n",
+    "    \"classification_type\": \"CPC\",\n",
+    "    \"description\": \"Real Cooperative Patent Classification (CPC) labels from PatentBERT training data\"\n",
+    "}\n",
+    "\n",
+    "# Save to model directory\n",
+    "model_dir = \"/tmp/patentbert_conversion/pytorch_model\"\n",
+    "labels_file = os.path.join(model_dir, \"labels.json\")\n",
+    "\n",
+    "with open(labels_file, 'w', encoding='utf-8') as f:\n",
+    "    json.dump(label_config, f, indent=2, ensure_ascii=False)\n",
+    "\n",
+    "print(f\"✅ Labels saved to: {labels_file}\")\n",
+    "\n",
+    "# Update model configuration to include labels\n",
+    "config_file = os.path.join(model_dir, \"config.json\")\n",
+    "\n",
+    "if os.path.exists(config_file):\n",
+    "    with open(config_file, 'r') as f:\n",
+    "        config = json.load(f)\n",
+    "    \n",
+    "    # Add labels to config\n",
+    "    config[\"id2label\"] = label_config[\"id2label\"]\n",
+    "    config[\"label2id\"] = label_config[\"label2id\"]\n",
+    "    \n",
+    "    # Save updated config\n",
+    "    with open(config_file, 'w', encoding='utf-8') as f:\n",
+    "        json.dump(config, f, indent=2, ensure_ascii=False)\n",
+    "    \n",
+    "    print(\"✅ Configuration updated with real CPC labels\")\n",
+    "else:\n",
+    "    print(\"⚠️ config.json file not found\")\n",
+    "\n",
+    "# Create detailed README with REAL CPC labels and distribution\n",
+    "section_descriptions = {\n",
+    "    'A': 'Human Necessities - Agriculture, Food, Health, Sports',\n",
+    "    'B': 'Performing Operations; Transporting - Manufacturing, Transport',\n",
+    "    'C': 'Chemistry; Metallurgy - Chemical processes, Materials',\n",
+    "    'D': 'Textiles; Paper - Fibers, Fabrics, Paper-making',\n",
+    "    'E': 'Fixed Constructions - Building, Mining, Roads',\n",
+    "    'F': 'Mechanical Engineering; Lightning; Heating; Weapons; Blasting',\n",
+    "    'G': 'Physics - Optics, Acoustics, Computing, Measuring',\n",
+    "    'H': 'Electricity - Electronics, Power generation, Communication',\n",
+    "    'Y': 'General Tagging of New Technological Developments'\n",
+    "}\n",
+    "\n",
+    "readme_with_labels = f\"\"\"# PatentBERT - PyTorch\n",
+    "\n",
+    "BERT model specialized for patent classification using the **real CPC (Cooperative Patent Classification) system** from the original PatentBERT training data.\n",
+    "\n",
+    "## 📊 Specifications\n",
+    "\n",
+    "- **Output classes**: {len(cpc_labels)} (real CPC labels)\n",
+    "- **Classification system**: CPC (Cooperative Patent Classification)\n",
+    "- **Architecture**: BERT-base (768 hidden, 12 layers, 12 attention heads)\n",
+    "- **Vocabulary**: 30,522 tokens\n",
+    "- **Format**: SafeTensors\n",
+    "\n",
+    "## 🏷️ CPC Classes (Real Distribution)\n",
+    "\n",
+    "The model predicts classes according to the authentic CPC system used in PatentBERT training:\n",
+    "\n",
+    "### Main Sections (Actual Counts)\n",
+    "\"\"\"\n",
+    "\n",
+    "# Add real distribution to README\n",
+    "for section in ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'Y']:\n",
+    "    if section in section_counts:\n",
+    "        count = section_counts[section]\n",
+    "        desc = section_descriptions.get(section, f'Section {section}')\n",
+    "        readme_with_labels += f\"- **{section} ({count} classes)**: {desc}\\n\"\n",
+    "\n",
+    "readme_with_labels += f\"\"\"\n",
+    "### Example Real Classes\n",
+    "\n",
+    "- `A01B`: SOIL WORKING IN AGRICULTURE OR FORESTRY\n",
+    "- `B25J`: MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES\n",
+    "- `C07D`: HETEROCYCLIC COMPOUNDS\n",
+    "- `G06F`: ELECTRIC DIGITAL DATA PROCESSING\n",
+    "- `H04L`: TRANSMISSION OF DIGITAL INFORMATION\n",
+    "\n",
+    "## 🚀 Usage\n",
+    "\n",
+    "```python\n",
+    "from transformers import BertForSequenceClassification, BertTokenizer\n",
+    "import json\n",
+    "import torch\n",
+    "\n",
+    "# Load model and tokenizer\n",
+    "model = BertForSequenceClassification.from_pretrained('ZoeYou/patentbert-pytorch')\n",
+    "tokenizer = BertTokenizer.from_pretrained('ZoeYou/patentbert-pytorch')\n",
+    "\n",
+    "# Inference example\n",
+    "text = \"A method for producing synthetic materials with enhanced thermal properties...\"\n",
+    "inputs = tokenizer(text, return_tensors=\"pt\", max_length=512, truncation=True, padding=True)\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    outputs = model(**inputs)\n",
+    "    predictions = outputs.logits.softmax(dim=-1)\n",
+    "\n",
+    "# Get prediction\n",
+    "predicted_class_id = predictions.argmax().item()\n",
+    "confidence = predictions.max().item()\n",
+    "\n",
+    "# Use model labels (real CPC codes)\n",
+    "predicted_label = model.config.id2label[predicted_class_id]\n",
+    "\n",
+    "\n",
+    "print(f\"Predicted CPC class: {{predicted_label}} (ID: {{predicted_class_id}})\")\n",
+    "print(f\"Confidence: {{confidence:.2%}}\")\n",
+    "```\n",
+    "\n",
+    "## 📁 Included Files\n",
+    "\n",
+    "- `model.safetensors`: Model weights (420 MB)\n",
+    "- `config.json`: Configuration with integrated real CPC labels\n",
+    "- `vocab.txt`: Tokenizer vocabulary\n",
+    "- `tokenizer_config.json`: Tokenizer configuration\n",
+    "- `labels.json`: Complete real CPC label mapping ({len(cpc_labels)} authentic labels)\n",
+    "- `README.md`: This documentation\n",
+    "\n",
+    "## 🔬 Performance\n",
+    "\n",
+    "This model was trained on a large patent corpus to automatically classify documents according to the real CPC system, using the exact same {len(cpc_labels)} CPC codes from the original PatentBERT training data.\n",
+    "\n",
+    "## 📖 References\n",
+    "\n",
+    "- [Cooperative Patent Classification (CPC)](https://www.cooperativepatentclassification.org/)\n",
+    "- [Original PatentBERT Paper](https://arxiv.org/abs/2103.02557)\n",
+    "\n",
+    "## 📝 Citation\n",
+    "\n",
+    "If you use this model, please cite the original PatentBERT work and mention this PyTorch conversion.\n",
+    "\"\"\"\n",
+    "\n",
+    "# Save updated README\n",
+    "readme_file = os.path.join(model_dir, \"README.md\")\n",
+    "with open(readme_file, 'w', encoding='utf-8') as f:\n",
+    "    f.write(readme_with_labels)\n",
+    "\n",
+    "print(\"✅ README updated with REAL CPC label documentation\")\n",
+    "\n",
+    "# Summary of created/updated files\n",
+    "print(\"\\n📁 Added/updated files:\")\n",
+    "print(f\"   • labels.json - Complete mapping of {len(cpc_labels)} REAL CPC labels\")\n",
+    "print(f\"   • config.json - Updated configuration with authentic id2label/label2id\")\n",
+    "print(f\"   • README.md - Complete documentation with real CPC distribution\")\n",
+    "\n",
+    "print(\"\\n🎯 Model is now ready for upload with AUTHENTIC CPC labels!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted CPC class: A63B (ID: 76)\n",
+      "Confidence: 99.51%\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import BertForSequenceClassification, BertTokenizer\n",
+    "import torch\n",
+    "\n",
+    "# Load model and tokenizer\n",
+    "model = BertForSequenceClassification.from_pretrained('ZoeYou/patentbert-pytorch')\n",
+    "tokenizer = BertTokenizer.from_pretrained('ZoeYou/patentbert-pytorch')\n",
+    "\n",
+    "# Inference example\n",
+    "text = \"A device designed to spin in a user's hands may include a body with a centrally mounted ball bearing positioned within a center orifice of the body, wherein an outer race of the ball bearing is attached to the frame; a button made of a pair of bearing caps attached to one another through the ball bearing and clamped against an inner race of the ball bearing, such that when the button is held between a user's thumb and finger, the body freely rotates about the ball bearing; and a plurality of weights distributed at opposite ends of the body, creating at least a bipolar weight distribution.\"\n",
+    "inputs = tokenizer(text, return_tensors=\"pt\", max_length=512, truncation=True, padding=True)\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    outputs = model(**inputs)\n",
+    "    predictions = outputs.logits.softmax(dim=-1)\n",
+    "\n",
+    "# Get prediction\n",
+    "predicted_class_id = predictions.argmax().item()\n",
+    "confidence = predictions.max().item()\n",
+    "\n",
+    "# Use model labels (real CPC codes)\n",
+    "predicted_label = model.config.id2label[predicted_class_id]\n",
+    "\n",
+    "print(f\"Predicted CPC class: {predicted_label} (ID: {predicted_class_id})\")\n",
+    "print(f\"Confidence: {confidence:.2%}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'A63B'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.config.id2label[76]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "collapsed_sections": [],
+   "name": "PatentBERT",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "simcse",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.23"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}