Update model card with explicit dataset utilization breakdown and training code link

README.md

@@ -24,10 +24,36 @@ This repository contains a **5.0 Million Parameter Causal Language Model** train
 
 The model is specialized in **Linux Terminal Commands, Shell Automation, and Multilingual Text Generation** (English, Indonesian, Spanish, French, German).
 
-## Model Architecture
+---
+
+## 📊 Dataset Breakdown & Utilization
+
+The model was trained on **100,000,000 Tokens** mixed across three distinct sources:
+
+| Dataset Name | Source / Hugging Face ID | Token Count | Share (%) | Utilization Details |
+| :--- | :--- | :--- | :--- | :--- |
+| **Linux Terminal & CLI Engine** | Synthesized Shell Engine | **~20.0 Million** | **20%** | **100% Fully Utilized**: Synthesized Linux CLI commands (`cd ..`, `ls -la`, `mkdir`, `grep`, `git`, `chmod`, `curl`, Q&A pairs). |
+| **English General Text** | [`wikitext`](https://huggingface.co/datasets/wikitext) (`wikitext-2-raw-v1`) | **~24.0 Million** | **24%** | **Streamed Sample**: Streamed line-by-line via Hugging Face `load_dataset("wikitext", streaming=True)`. |
+| **Multilingual Wikipedia** | [`wikimedia/wikipedia`](https://huggingface.co/datasets/wikimedia/wikipedia) | **~56.0 Million** | **56%** | **Streamed Multilingual Sample**: Streamed across 4 language sub-splits (Indonesian `id`, Spanish `es`, French `fr`, German `de`). |
+| **TOTAL** | Mixed Corpus | **100.0 Million** | **100%** | **Chinchilla Compute-Optimal** ($20\times$ params) |
+
+---
+
+## 📂 Complete Training Source Code
+
+The full, self-contained training codebase is included directly in this repository inside the [`/training_code`](./training_code) folder:
+
+* [`training_code/main_kaggle.py`](./training_code/main_kaggle.py): Complete Kaggle GPU standalone training script.
+* [`training_code/train.py`](./training_code/train.py): Main PyTorch model architecture, loss functions, and HF auto-upload.
+* [`training_code/terminal_dataset.py`](./training_code/terminal_dataset.py): CLI command generator and shell interaction builder.
+* [`training_code/tokenizer_builder.py`](./training_code/tokenizer_builder.py): Custom 4,096 BPE Tokenizer trainer.
+
+---
+
+## ⚙️ Model Architecture
 
 * **Total Trainable Parameters**: 4,984,064 (~4.98M / 5.0M)
-* **Architecture**: Decoder-only Transformer (LLaMA style)
+* **Architecture**: Decoder-only Transformer (LLaMA style with SwiGLU & RMSNorm)
 * **Vocabulary Size**: 4,096 (Byte-Pair Encoding Tokenizer)
 * **Hidden Dimension (`d_model`)**: 256
 * **Number of Layers (`n_layer`)**: 6
@@ -36,16 +62,9 @@ The model is specialized in **Linux Terminal Commands, Shell Automation, and Mul
 * **Context Window (`max_seq_len`)**: 256 tokens
 * **Weight Tying**: Tied Embedding and LM Head weights
 
-## Training Details
-
-* **Token Budget**: 100,000,000 Tokens (Chinchilla Optimal: 20 tokens per parameter)
-* **Dataset Composition**:
-  * **Terminal CLI & Commands**: 20% (Bash commands, `cd ..`, `ls -la`, `mkdir`, `grep`, `git`, `chmod`, `curl`, Q&A pairs)
-  * **English Text**: 24% (`wikitext-103-v1` + technical corpus)
-  * **Multilingual Text**: 56% (Indonesian, Spanish, French, German Wikipedia & general text)
-* **Hardware**: Kaggle NVIDIA GPU (Dual Tesla T4 / P100) with FP16 AMP Mixed Precision.
+---
 
-## Usage & Inference Example (PyTorch)
+## 💻 Usage & Inference Example (PyTorch)
 
 ```python
 import torch