Update README.md

README.md

@@ -1,14 +1,17 @@
 ---
-library_name: 'custom'
+library_name: custom
 tags:
-  - custom-architecture
-  - numpy
-  - chatbot
-  - text-generation
+- custom-architecture
+- numpy
+- chatbot
+- text-generation
 license: mit
 metrics:
-  - loss
-  - perplexity
+- loss
+- perplexity
+language:
+- en
+pipeline_tag: text-generation
 ---
 
 # HRAN Chatbot Model Card
@@ -17,7 +20,7 @@ metrics:
 
 The architecture is strictly derived from concepts in Simon Haykin's Neural Networks and Learning Machines (3rd Ed.), actively challenging modern transformer defaults by replacing dot-product attention and standard activations with biologically and mathematically grounded alternatives.
 
-*   **Developer**: Phase-Technologies
+*   **Developer**: Soham Pal
 *   **Model Type**: Custom Sequence-to-Sequence Language Model
 *   **Parameters**: ~1.01 Million
 *   **Framework**: Pure NumPy
@@ -32,6 +35,11 @@ HRAN abandons several standard transformer conventions in favor of experimental
 *   **Lateral Inhibition Gate (Ch.9)**: Introduces competitive learning where winning activations are amplified and weak ones suppressed, producing sparse, discriminative representations.
 *   **Wiener-SNR Gradient Scaling (Ch.3)**: Scales parameter updates by local signal-to-noise ratio, allowing high-signal weights to learn quickly while suppressing noisy weight updates.
 
+## Loss Graph
+
+![HRAN Training Loss](hran_training_loss.png)
+
+
 ## Training Data
 The model was trained on a highly curated, 100% original dataset of 235 question-answer pairs (augmented to 1,040 samples). The dataset spans deep topics including neural network architecture, philosophy, physics, mathematics, and Haykin's specific theories.
 
@@ -80,4 +88,4 @@ model.load(weights_path)
 # 5. Generate Text
 response = hran.generate_response(model, tokenizer, "What is attention?")
 print(response)
-```
+```