Update README.md

README.md

@@ -28,7 +28,10 @@ The Seq2Seq Reverser model is a specialized sequence-to-sequence model trained t
 ### Model Architecture
 
 The model uses a sequence-to-sequence architecture with:
-- Encoder-decoder transformer architecture
+- Transformer decoder with 2 layers
+- 8 attention heads
+- 768-dimensional embeddings
+- 2048-dimensional feed-forward networks
 - Specialized tokenizer for crypto market terminology
 - Optimized for embedding vector reconstruction
 
@@ -37,13 +40,14 @@ The model uses a sequence-to-sequence architecture with:
 The model can be used through the Aparecium Python package:
 
 ```python
-from aparecium.models.seq2seqreverser import ModelManager
+from aparecium import Seq2SeqReverser
 
-# Initialize the model manager
-manager = ModelManager()
+# Load the pre-trained model from Hugging Face Hub
+reverser = Seq2SeqReverser.from_pretrained("SentiChain/aparecium-seq2seq-reverser")
 
-# The model will be automatically downloaded when needed
-model_path = manager.get_model_path()
+# Generate text from embedding vectors
+recovered_text = reverser.generate_text(source_rep)
+print(recovered_text)
 ```
 
 ### Installation
@@ -75,11 +79,12 @@ This model is released under the MIT License.
 If you use this model in your research, please cite:
 
 ```bibtex
-@software{aparecium_seq2seq_reverser,
-  title = {Aparecium Seq2Seq Reverser},
-  author = {SentiChain},
-  url = {https://huggingface.co/SentiChain/aparecium-seq2seq-reverser},
-  year = {2024},
+@software{aparecium2025,
+  author = {Chen, Edward},
+  title = {Aparecium: Text Reconstruction from Embedding Vectors},
+  year = {2025},
+  publisher = {GitHub},
+  url = {https://github.com/SentiChain/aparecium}
 }
 ```