# 🚀 Transformer From Scratch (PyTorch)

> A complete implementation of the **Transformer architecture** from the paper **Attention Is All You Need**, built entirely with PyTorch.

<p align="center">
  <img src="https://img.shields.io/badge/Python-3.10+-3776AB?logo=python&logoColor=white">
  <img src="https://img.shields.io/badge/PyTorch-2.x-EE4C2C?logo=pytorch&logoColor=white">
  <img src="https://img.shields.io/badge/License-MIT-success">
  <img src="https://img.shields.io/badge/Status-Active-brightgreen">
</p>

---

## 📖 Overview

The Transformer changed Natural Language Processing by replacing recurrent networks with **self-attention**, allowing models to process entire sequences in parallel.

This repository implements every major component **from scratch** without using `torch.nn.Transformer`.

It is designed for:

- 🎓 Students learning Transformers
- 👨‍💻 Deep Learning practitioners
- 🔬 AI researchers
- 💼 Interview preparation
- 🚀 Building custom NLP models

---

## ✨ Features

- Token Embeddings
- Sinusoidal Positional Encoding
- Multi-Head Self Attention
- Masked Multi-Head Attention
- Encoder–Decoder Attention
- Position-wise Feed Forward Network
- Residual Connections
- Layer Normalization
- Stacked Encoder Layers
- Stacked Decoder Layers
- Final Vocabulary Projection

---

# 🏗️ Overall Architecture

```mermaid
flowchart TD

A[Source Tokens]
B[Embedding]
C[Positional Encoding]

D["Encoder × N"]

E[Encoder Memory]

F[Target Tokens]
G[Embedding]
H[Positional Encoding]

I["Decoder × N"]

J[Linear Layer]

K[Vocabulary Probabilities]

A --> B --> C --> D --> E

F --> G --> H --> I

E --> I

I --> J --> K
```

---

# 🧩 Transformer Components

```mermaid
graph TD

Transformer

Transformer --> Embedding
Transformer --> PositionalEncoding
Transformer --> Encoder
Transformer --> Decoder
Transformer --> Linear

Encoder --> MultiHeadAttention
Encoder --> FeedForward
Encoder --> LayerNorm

Decoder --> MaskedAttention
Decoder --> CrossAttention
Decoder --> FeedForward2
Decoder --> LayerNorm2
```

---

# ⚙️ Encoder Block

Each encoder layer consists of:

```text
Input
   │
   ▼
Multi-Head Self Attention
   │
Add & LayerNorm
   │
Feed Forward Network
   │
Add & LayerNorm
   │
Output
```

---

# ⚙️ Decoder Block

Each decoder layer consists of:

```text
Input
   │
   ▼
Masked Multi-Head Attention
   │
Add & LayerNorm
   │
Cross Attention
   │
Add & LayerNorm
   │
Feed Forward Network
   │
Add & LayerNorm
   │
Output
```

---

# 📂 Project Structure

```text
transformer-from-scratch/

├── model.py
├── encoder.py
├── decoder.py
├── attention.py
├── positional_encoding.py
├── config.py
├── train.py
├── inference.py
├── README.md
│
└── notebooks/
```

---

# ⚡ Model Configuration

| Hyperparameter | Value |
|----------------|------:|
| Encoder Layers | 6 |
| Decoder Layers | 6 |
| Attention Heads | 8 |
| Embedding Size | 512 |
| Feed Forward Size | 2048 |
| Maximum Sequence Length | 5000 |

---

# 🚀 Quick Start

```python
import torch
from model import Transformer

src = torch.randint(0, 10000, (64, 20))
tgt = torch.randint(0, 12000, (64, 15))

model = Transformer(
    src_vocab_size=10000,
    tgt_vocab_size=12000,
    num_heads=8,
    num_layers=6,
    emb_dim=512,
    nn_dim=2048
)

output = model(src, tgt)

print(output.shape)
```

Output

```python
torch.Size([64, 15, 12000])
```

---

# 🔄 Forward Pass

```mermaid
sequenceDiagram

participant Source
participant Encoder
participant Decoder
participant Output

Source->>Encoder: Source Tokens

Encoder->>Encoder: Self Attention

Encoder-->>Decoder: Encoder Memory

Decoder->>Decoder: Masked Self Attention

Decoder->>Encoder: Cross Attention

Decoder->>Output: Vocabulary Logits
```

---

# 🏋️ Training

```python
criterion = nn.CrossEntropyLoss()

optimizer = torch.optim.Adam(
    model.parameters(),
    lr=1e-4
)
```

---

# 📚 What You'll Learn

After studying this repository, you'll understand:

- Self-Attention
- Multi-Head Attention
- Positional Encoding
- Encoder Architecture
- Decoder Architecture
- Residual Connections
- Layer Normalization
- Feed Forward Networks
- Sequence-to-Sequence Modeling
- Machine Translation Pipeline

---

# 🚧 Future Improvements

- Greedy Decoding
- Beam Search
- Label Smoothing
- Learning Rate Scheduler
- Mixed Precision Training
- Flash Attention
- KV Cache
- Weight Sharing
- Byte Pair Encoding (BPE)
- Hugging Face Checkpoint Support
- ONNX Export

---

# 📄 Reference Paper

**Attention Is All You Need**

Ashish Vaswani et al.

NeurIPS 2017

---

# ⭐ Support

If this project helped you understand Transformers, consider giving it a ⭐ on GitHub.

It helps others discover the project and motivates future improvements.

---

# 📜 License

Released under the **MIT License**.