Upload PatentBERT PyTorch model

BERT model fine-tuned for patent classification, converted from TensorFlow to PyTorch.

Specifications:
- Format: SafeTensors
- Classes: Auto-detected from config.json
- Conversion: TensorFlow 1.15 → PyTorch via transformers

Included files:
labels.json, README.md, tokenizer_config.json, vocab.txt, model.safetensors, config.json

README.md

@@ -1,13 +1,6 @@
----
-license: gpl-3.0
-language:
-- en
-base_model:
-- google-bert/bert-base-uncased
----
 # PatentBERT - PyTorch
 
-BERT model specialized for patent classification using the **CPC (Cooperative Patent Classification) system**. ([PatentBert](https://github.com/jiehsheng/PatentBERT) converted into PyTorch version)
+BERT model specialized for patent classification using the **real CPC (Cooperative Patent Classification) system** from the original PatentBERT training data.
 
 ## 📊 Specifications
 
@@ -64,7 +57,7 @@ predicted_class_id = predictions.argmax().item()
 confidence = predictions.max().item()
 
 # Use model labels (real CPC codes)
-predicted_label = model.config.id2label[predicted_class_id]
+predicted_label = model.config.id2label[str(predicted_class_id)]
 
 print(f"Predicted CPC class: {predicted_label} (ID: {predicted_class_id})")
 print(f"Confidence: {confidence:.2%}")
@@ -87,7 +80,8 @@ This model was trained on a large patent corpus to automatically classify docume
 
 - [Cooperative Patent Classification (CPC)](https://www.cooperativepatentclassification.org/)
 - [Original PatentBERT Paper](https://arxiv.org/abs/2103.02557)
+- [Hugging Face Transformers](https://huggingface.co/transformers/)
 
 ## 📝 Citation
 
-If you use this model, please cite the original PatentBERT work and mention this PyTorch conversion.
+If you use this model, please cite the original PatentBERT work and mention this PyTorch conversion.

config.json

@@ -1336,5 +1336,6 @@
   "transformers_version": "4.53.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30522,
+  "num_labels": 656
 }