File size: 2,749 Bytes
2f9e2c6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
import torch
def column_split(x, num_heads, head_size):
"""Split a tensor with `num_heads` alongside the head dimension, instead of
across heads. Fixed to three projections
"""
x_reshaped = x.reshape(
x.shape[0],
num_heads,
3 * head_size,
)
x2, x1, v = (
x_reshaped[:, :, :head_size],
x_reshaped[
:,
:,
head_size : 2 * head_size,
],
x_reshaped[:, :, 2 * head_size :],
)
x2, x1, v = (
x2.reshape(x2.shape[0], -1),
x1.reshape(x1.shape[0], -1),
v.reshape(v.shape[0], -1),
)
return x2, x1, v
def get_init_from_string(init_str):
if type(init_str) == str:
if init_str == "torch.nn.init.zeros_":
return torch.nn.init.zeros_
elif init_str == "torch.nn.init.xavier_uniform_":
return torch.nn.init.xavier_uniform_
elif init_str == "torch.nn.init.xavier_normal_":
return torch.nn.init.xavier_normal_
else:
raise ValueError(f"Unrecognized init {init_str}")
def print_rank_0(message, debug=False, end="\n"):
"""Print from rank 0 only."""
if torch.distributed.is_initialized():
if torch.distributed.get_rank() == 0:
print(message, flush=True, end=end)
else:
print(message, flush=True, end=end)
class dotdict(dict):
"""dot.notation access to dictionary attributes"""
__getattr__ = dict.get
__setattr__ = dict.__setitem__
__delattr__ = dict.__delitem__
def ensure_divisibility(numerator, denominator):
"""Ensure that numerator is divisible by the denominator."""
assert numerator % denominator == 0, "{} is not divisible by {}".format(numerator, denominator)
def divide(numerator, denominator):
"""Ensure that numerator is divisible by the denominator and return
the division value."""
ensure_divisibility(numerator, denominator)
return numerator // denominator
class VocabUtility:
"""Split the vocabulary into `world_size` chunks amd return the
first and last index of the vocabulary belonging to the `rank`
partition: Note that indices in [first, last]"""
@staticmethod
def vocab_range_from_per_partition_vocab_size(per_partition_vocab_size, rank, world_size):
index_f = rank * per_partition_vocab_size
index_l = index_f + per_partition_vocab_size
return index_f, index_l
@staticmethod
def vocab_range_from_global_vocab_size(global_vocab_size, rank, world_size):
per_partition_vocab_size = divide(global_vocab_size, world_size)
return VocabUtility.vocab_range_from_per_partition_vocab_size(
per_partition_vocab_size, rank, world_size
)
|