# 🧠 DarkAIs PyTorch Transformer Trainer Starter
import torch
import torch.nn as nn
import math

class ScaledDotProductAttention(nn.Module):
    def __init__(self, d_k):
        super().__init__()
        self.d_k = d_k

    def forward(self, q, k, v, mask=None):
        scores = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.d_k)
        if mask is not None:
            scores = scores.masked_fill(mask == 0, -1e9)
        attn = torch.softmax(scores, dim=-1)
        return torch.matmul(attn, v), attn

print("✓ DarkAIs PyTorch Transformer Ready.")