Spaces:
Running
Running
File size: 6,806 Bytes
7c4b306 |
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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
# coding=utf-8
# Copyright 2018 The OpenAI Team Authors and HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""PyTorch OpenAI GPT-2 model."""
import math
import os
from dataclasses import dataclass
from typing import Optional, Tuple, Union
import torch
import torch.utils.checkpoint
from packaging import version
from torch import nn
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
from transformers.models.gpt2.modeling_gpt2 import load_tf_weights_in_gpt2, GPT2LMHeadModel, GPT2MLP, GPT2Attention, GPT2Block, GPT2Model
from transformers.activations import ACT2FN
from transformers.modeling_outputs import (
BaseModelOutputWithPastAndCrossAttentions,
CausalLMOutputWithCrossAttentions,
SequenceClassifierOutputWithPast,
TokenClassifierOutput,
)
from transformers.modeling_utils import PreTrainedModel, SequenceSummary
from transformers.pytorch_utils import Conv1D, find_pruneable_heads_and_indices, prune_conv1d_layer
from transformers.utils import (
ModelOutput,
logging,
)
from transformers.utils.model_parallel_utils import assert_device_map, get_device_map
from transformers.models.gpt2.configuration_gpt2 import GPT2Config
if version.parse(torch.__version__) >= version.parse("1.6"):
is_amp_available = True
from torch.cuda.amp import autocast
else:
is_amp_available = False
class ThisGPT2Config(GPT2Config):
model_type = "this_gpt2"
def __init__(
self,
cross_attention_reduce_factor = 1,
**kwargs,
):
super().__init__(**kwargs)
self.cross_attention_reduce_factor = cross_attention_reduce_factor
class ThisGPT2Attention(GPT2Attention):
def __init__(self, config, is_cross_attention=False, layer_idx=None):
super().__init__(config, is_cross_attention, layer_idx)
#print("this gpt2")
#print("self.is_cross_attention = is_cross_attention", self.is_cross_attention, is_cross_attention)
self.cross_attention_reduce_factor = config.cross_attention_reduce_factor
if self.is_cross_attention:
self.c_attn = Conv1D(int(2 / self.cross_attention_reduce_factor * self.embed_dim),
self.embed_dim)
self.q_attn = Conv1D(int(self.embed_dim / self.cross_attention_reduce_factor), self.embed_dim)
self.c_proj = Conv1D(self.embed_dim, int(self.embed_dim / self.cross_attention_reduce_factor))
else:
self.c_attn = Conv1D(3 * self.embed_dim, self.embed_dim)
self.c_proj = Conv1D(self.embed_dim, self.embed_dim)
def forward(
self,
hidden_states: Optional[Tuple[torch.FloatTensor]],
layer_past: Optional[Tuple[torch.Tensor]] = None,
attention_mask: Optional[torch.FloatTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.Tensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
use_cache: Optional[bool] = False,
output_attentions: Optional[bool] = False,
) -> Tuple[Union[torch.Tensor, Tuple[torch.Tensor]], ...]:
if encoder_hidden_states is not None:
if not hasattr(self, "q_attn"):
raise ValueError(
"If class is used as cross attention, the weights `q_attn` have to be defined. "
"Please make sure to instantiate class with `GPT2Attention(..., is_cross_attention=True)`."
)
split_size = int(self.split_size / self.cross_attention_reduce_factor)
head_dim = int(self.head_dim / self.cross_attention_reduce_factor)
query = self.q_attn(hidden_states)
key, value = self.c_attn(encoder_hidden_states).split(split_size, dim=2)
attention_mask = encoder_attention_mask
query = self._split_heads(query, self.num_heads, head_dim)
key = self._split_heads(key, self.num_heads, head_dim)
value = self._split_heads(value, self.num_heads, head_dim)
else:
query, key, value = self.c_attn(hidden_states).split(self.split_size, dim=2)
query = self._split_heads(query, self.num_heads, self.head_dim)
key = self._split_heads(key, self.num_heads, self.head_dim)
value = self._split_heads(value, self.num_heads, self.head_dim)
if layer_past is not None:
past_key, past_value = layer_past
key = torch.cat((past_key, key), dim=-2)
value = torch.cat((past_value, value), dim=-2)
if use_cache is True:
present = (key, value)
else:
present = None
if self.reorder_and_upcast_attn:
attn_output, attn_weights = self._upcast_and_reordered_attn(query, key, value, attention_mask, head_mask)
else:
attn_output, attn_weights = self._attn(query, key, value, attention_mask, head_mask)
attn_output = self._merge_heads(attn_output, self.num_heads, int(self.head_dim / self.cross_attention_reduce_factor))
attn_output = self.c_proj(attn_output)
attn_output = self.resid_dropout(attn_output)
outputs = (attn_output, present)
if output_attentions:
outputs += (attn_weights,)
return outputs # a, present, (attentions)
class ThisGPT2Block(GPT2Block):
def __init__(self, config, layer_idx=None):
super().__init__(config, layer_idx)
hidden_size = config.hidden_size
if config.add_cross_attention:
self.crossattention = ThisGPT2Attention(config, is_cross_attention=True, layer_idx=layer_idx)
self.ln_cross_attn = nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)
class ThisGPT2Model(GPT2Model):
def __init__(self, config):
super().__init__(config)
self.h = nn.ModuleList([ThisGPT2Block(config, layer_idx=i) for i in range(config.num_hidden_layers)])
class ThisGPT2LMHeadModel(GPT2LMHeadModel):
config_class = ThisGPT2Config
def __init__(self, config):
super().__init__(config)
self.transformer = ThisGPT2Model(config)
|