Butanium

"""
A minimal pytorch implementation of a multi-head attention transformer inspired by nanoGPT
"""
from dataclasses import dataclass
import torch.nn as nn
import torch.nn.functional as F
import torch as th
import numpy as np

class SelfAttention(nn.Module):

Butanium

import sys
import math
import numpy as np

REST = "REST"
WAIT = "WAIT"


# Auto-generated code below aims at helping you parse
# the standard input according to the problem statement.