Your commits
deserve better.

A complete GPT in 243 lines of pure Python — no PyTorch, no NumPy, just gradients and backpropagation from scratch.

class Value:
  """Stores a single scalar value and its gradient."""

  def __init__(self, data, _children=(), _op=''):
    self.data = data
    self.grad = 0
    self._backward = lambda: None
    self._prev = set(_children)
    self._op = _op

  def __add__(self, other):
    other = other if isinstance(other, Value) else Value(other)
    out = Value(self.data + other.data, (self, other), '+')
    return out