Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -21,7 +21,6 @@
|
||||
|
||||
from collections.abc import Iterable
|
||||
from itertools import islice
|
||||
from typing import Optional, Union
|
||||
|
||||
import torch
|
||||
from torch import nn
|
||||
@@ -64,8 +63,8 @@ class GPTJAttention(nn.Module):
|
||||
def __init__(
|
||||
self,
|
||||
config: GPTJConfig,
|
||||
cache_config: Optional[CacheConfig] = None,
|
||||
quant_config: Optional[QuantizationConfig] = None,
|
||||
cache_config: CacheConfig | None = None,
|
||||
quant_config: QuantizationConfig | None = None,
|
||||
prefix: str = "",
|
||||
):
|
||||
super().__init__()
|
||||
@@ -130,7 +129,7 @@ class GPTJMLP(nn.Module):
|
||||
self,
|
||||
intermediate_size: int,
|
||||
config: GPTJConfig,
|
||||
quant_config: Optional[QuantizationConfig] = None,
|
||||
quant_config: QuantizationConfig | None = None,
|
||||
):
|
||||
super().__init__()
|
||||
hidden_size = config.n_embd
|
||||
@@ -157,8 +156,8 @@ class GPTJBlock(nn.Module):
|
||||
def __init__(
|
||||
self,
|
||||
config: GPTJConfig,
|
||||
cache_config: Optional[CacheConfig] = None,
|
||||
quant_config: Optional[QuantizationConfig] = None,
|
||||
cache_config: CacheConfig | None = None,
|
||||
quant_config: QuantizationConfig | None = None,
|
||||
prefix: str = "",
|
||||
):
|
||||
super().__init__()
|
||||
@@ -218,9 +217,9 @@ class GPTJModel(nn.Module):
|
||||
self,
|
||||
input_ids: torch.Tensor,
|
||||
position_ids: torch.Tensor,
|
||||
intermediate_tensors: Optional[IntermediateTensors],
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
) -> Union[torch.Tensor, IntermediateTensors]:
|
||||
intermediate_tensors: IntermediateTensors | None,
|
||||
inputs_embeds: torch.Tensor | None = None,
|
||||
) -> torch.Tensor | IntermediateTensors:
|
||||
if get_pp_group().is_first_rank:
|
||||
if inputs_embeds is not None:
|
||||
hidden_states = inputs_embeds
|
||||
@@ -322,9 +321,9 @@ class GPTJForCausalLM(nn.Module, SupportsPP):
|
||||
self,
|
||||
input_ids: torch.Tensor,
|
||||
positions: torch.Tensor,
|
||||
intermediate_tensors: Optional[IntermediateTensors] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
) -> Union[torch.Tensor, IntermediateTensors]:
|
||||
intermediate_tensors: IntermediateTensors | None = None,
|
||||
inputs_embeds: torch.Tensor | None = None,
|
||||
) -> torch.Tensor | IntermediateTensors:
|
||||
hidden_states = self.transformer(
|
||||
input_ids, positions, intermediate_tensors, inputs_embeds
|
||||
)
|
||||
@@ -333,7 +332,7 @@ class GPTJForCausalLM(nn.Module, SupportsPP):
|
||||
def compute_logits(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
) -> Optional[torch.Tensor]:
|
||||
) -> torch.Tensor | None:
|
||||
logits = self.logits_processor(self.lm_head, hidden_states, self.lm_head.bias)
|
||||
return logits
|
||||
|
||||
|
||||
Reference in New Issue
Block a user