-
Notifications
You must be signed in to change notification settings - Fork 3
/
model.py
671 lines (573 loc) · 28.6 KB
/
model.py
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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
""" Adapted GPT-2 model for kg_mask support
This code is based on the GPT-2 model implementation from the transformers library.
We used version 4.5.1
The original code can be found here:
https://huggingface.co/transformers/v4.5.1/_modules/transformers/models/gpt2/modeling_gpt2.html
Changes marked with additional comments.
"""
import torch
import torch.nn as nn
from torch.nn import CrossEntropyLoss
from typing import Tuple
from transformers.utils import logging
from transformers.activations import ACT2FN
from transformers.models.gpt2 import GPT2PreTrainedModel
from transformers.utils.model_parallel_utils import assert_device_map, get_device_map
from transformers.modeling_outputs import CausalLMOutputWithCrossAttentions, BaseModelOutputWithPastAndCrossAttentions
from transformers.modeling_utils import Conv1D, find_pruneable_heads_and_indices, prune_conv1d_layer
logger = logging.get_logger(__name__)
#######################################################################################################################
# Attention class #
#######################################################################################################################
class Attention(nn.Module):
def __init__(self, nx, n_ctx, config, scale=False, is_cross_attention=False):
super().__init__()
n_state = nx # in Attention: n_state=768 (nx=n_embd)
# [switch nx => n_state from Block to Attention to keep identical to TF implem]
assert n_state % config.n_head == 0
self.register_buffer(
"bias", torch.tril(torch.ones((n_ctx, n_ctx), dtype=torch.uint8)).view(1, 1, n_ctx, n_ctx)
)
self.register_buffer("masked_bias", torch.tensor(-1e4))
self.n_head = config.n_head
self.split_size = n_state
self.scale = scale
self.is_cross_attention = is_cross_attention
if self.is_cross_attention:
self.c_attn = Conv1D(2 * n_state, nx)
self.q_attn = Conv1D(n_state, nx)
else:
self.c_attn = Conv1D(3 * n_state, nx)
self.c_proj = Conv1D(n_state, nx)
self.attn_dropout = nn.Dropout(config.attn_pdrop)
self.resid_dropout = nn.Dropout(config.resid_pdrop)
self.pruned_heads = set()
def prune_heads(self, heads):
if len(heads) == 0:
return
heads, index = find_pruneable_heads_and_indices(
heads, self.n_head, self.split_size // self.n_head, self.pruned_heads
)
index_attn = torch.cat([index, index + self.split_size, index + (2 * self.split_size)])
# Prune conv1d layers
self.c_attn = prune_conv1d_layer(self.c_attn, index_attn, dim=1)
self.c_proj = prune_conv1d_layer(self.c_proj, index, dim=0)
# Update hyper params
self.split_size = (self.split_size // self.n_head) * (self.n_head - len(heads))
self.n_head = self.n_head - len(heads)
self.pruned_heads = self.pruned_heads.union(heads)
def _attn(self, q, k, v, kg_masks, attention_mask=None, head_mask=None, output_attentions=False):
w = torch.matmul(q, k)
if self.scale:
w = w / (float(v.size(-1)) ** 0.5)
bs, nd, ns = w.size(0), w.size(-2), w.size(-1) # Changed by authors: Batch size is required.
if not self.is_cross_attention:
# if only "normal" attention layer implements causal mask
mask = self.bias[:, :, ns - nd : ns, :ns]
w = torch.where(mask.bool(), w, self.masked_bias.to(w.dtype))
# --- Manipulating the attention weights according to kg_mask -------------------------------------------------
# Create (dynamic) future mask mask
mask = torch.stack(bs * [self.bias[:, :, ns - nd: ns, :ns]], dim=0).view(-1, 1, ns, ns)
# Replace the kg sequence part with the kg_masks
amd, ams = kg_masks.size(-2), kg_masks.size(-1)
mask[:, 0, 0:amd, 0:ams] = kg_masks
# Mask zeros out
w = torch.where(mask.bool(), w, self.masked_bias.to(w.dtype))
# -------------------------------------------------------------------------------------------------------------
if attention_mask is not None:
# Apply the attention mask
w = w + attention_mask
w = nn.Softmax(dim=-1)(w)
w = self.attn_dropout(w)
# Mask heads if we want to
if head_mask is not None:
w = w * head_mask
outputs = (torch.matmul(w, v),)
if output_attentions:
outputs += (w,)
return outputs
def merge_heads(self, x):
x = x.permute(0, 2, 1, 3).contiguous()
new_x_shape = x.size()[:-2] + (x.size(-2) * x.size(-1),)
return x.view(*new_x_shape) # in Tensorflow implem: fct merge_states
def split_heads(self, x, k=False):
new_x_shape = x.size()[:-1] + (self.n_head, x.size(-1) // self.n_head)
x = x.view(*new_x_shape) # in Tensorflow implem: fct split_states
if k:
return x.permute(0, 2, 3, 1) # (batch, head, head_features, seq_length)
else:
return x.permute(0, 2, 1, 3) # (batch, head, seq_length, head_features)
def forward(
self,
hidden_states,
kg_masks, # Added by the authors.
layer_past=None,
attention_mask=None,
head_mask=None,
encoder_hidden_states=None,
encoder_attention_mask=None,
use_cache=False,
output_attentions=False,
):
if encoder_hidden_states is not None:
assert hasattr(
self, "q_attn"
), "If class is used as cross attention, the weights `q_attn` have to be defined. " \
"Please make sure to instantiate class with `Attention(..., is_cross_attention=True)`."
query = self.q_attn(hidden_states)
key, value = self.c_attn(encoder_hidden_states).split(self.split_size, dim=2)
attention_mask = encoder_attention_mask
else:
query, key, value = self.c_attn(hidden_states).split(self.split_size, dim=2)
query = self.split_heads(query)
key = self.split_heads(key, k=True)
value = self.split_heads(value)
if layer_past is not None:
past_key, past_value = layer_past[0].transpose(-2, -1), layer_past[1] # transpose back cf below
key = torch.cat((past_key, key), dim=-1)
value = torch.cat((past_value, value), dim=-2)
if use_cache is True:
present = (key.transpose(-2, -1), value) # transpose to have same shapes
else:
present = None
attn_outputs = self._attn(query, key, value, kg_masks, attention_mask, head_mask, output_attentions)
a = attn_outputs[0]
a = self.merge_heads(a)
a = self.c_proj(a)
a = self.resid_dropout(a)
return (a, present) + attn_outputs[1:] # a, present, (attentions)
#######################################################################################################################
# MLP class #
#######################################################################################################################
class MLP(nn.Module):
def __init__(self, n_state, config): # in MLP: n_state=3072 (4 * n_embd)
super().__init__()
nx = config.n_embd
self.c_fc = Conv1D(n_state, nx)
self.c_proj = Conv1D(nx, n_state)
self.act = ACT2FN[config.activation_function]
self.dropout = nn.Dropout(config.resid_pdrop)
def forward(self, x):
h = self.act(self.c_fc(x))
h2 = self.c_proj(h)
return self.dropout(h2)
#######################################################################################################################
# Block class #
#######################################################################################################################
class Block(nn.Module):
def __init__(self, n_ctx, config, scale=False):
super().__init__()
hidden_size = config.n_embd
inner_dim = config.n_inner if config.n_inner is not None else 4 * hidden_size
self.ln_1 = nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)
self.attn = Attention(hidden_size, n_ctx, config, scale)
self.ln_2 = nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)
if config.add_cross_attention:
self.crossattention = Attention(hidden_size, n_ctx, config, scale, is_cross_attention=True)
self.ln_cross_attn = nn.LayerNorm(hidden_size, eps=config.layer_norm_epsilon)
self.mlp = MLP(inner_dim, config)
def forward(
self,
hidden_states,
kg_masks, # Added by the authors.
layer_past=None,
attention_mask=None,
head_mask=None,
encoder_hidden_states=None,
encoder_attention_mask=None,
use_cache=False,
output_attentions=False,
):
attn_outputs = self.attn(
self.ln_1(hidden_states),
kg_masks=kg_masks, # Added by the authors.
layer_past=layer_past,
attention_mask=attention_mask,
head_mask=head_mask,
use_cache=use_cache,
output_attentions=output_attentions,
)
attn_output = attn_outputs[0] # output_attn: a, present, (attentions)
outputs = attn_outputs[1:]
# residual connection
hidden_states = attn_output + hidden_states
if encoder_hidden_states is not None:
# add one self-attention block for cross-attention
assert hasattr(
self, "crossattention"
), f"If `encoder_hidden_states` are passed, {self} has to be instantiated with cross-attention " \
f"layers by setting `config.add_cross_attention=True`"
cross_attn_outputs = self.crossattention(
self.ln_cross_attn(hidden_states),
attention_mask=attention_mask,
head_mask=head_mask,
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
output_attentions=output_attentions,
)
attn_output = cross_attn_outputs[0]
# residual connection
hidden_states = hidden_states + attn_output
outputs = outputs + cross_attn_outputs[2:] # add cross attentions if we output attention weights
feed_forward_hidden_states = self.mlp(self.ln_2(hidden_states))
# residual connection
hidden_states = hidden_states + feed_forward_hidden_states
if use_cache:
outputs = (hidden_states,) + outputs
else:
outputs = (hidden_states,) + outputs[1:]
return outputs # hidden_states, present, (attentions, cross_attentions)
#######################################################################################################################
# GPT2 Model class (with kg_masks support) #
#######################################################################################################################
class GPT2Model(GPT2PreTrainedModel):
def __init__(self, config):
super().__init__(config)
self.wte = nn.Embedding(config.vocab_size, config.n_embd)
self.wpe = nn.Embedding(config.n_positions, config.n_embd)
self.drop = nn.Dropout(config.embd_pdrop)
self.h = nn.ModuleList([Block(config.n_ctx, config, scale=True) for _ in range(config.n_layer)])
self.ln_f = nn.LayerNorm(config.n_embd, eps=config.layer_norm_epsilon)
self.init_weights()
# Model parallel
self.model_parallel = False
self.device_map = None
def parallelize(self, device_map=None):
# Check validity of device_map
self.device_map = (
get_device_map(len(self.h), range(torch.cuda.device_count())) if device_map is None else device_map
)
assert_device_map(self.device_map, len(self.h))
self.model_parallel = True
self.first_device = "cpu" if "cpu" in self.device_map.keys() else "cuda:" + str(min(self.device_map.keys()))
self.last_device = "cuda:" + str(max(self.device_map.keys()))
self.wte = self.wte.to(self.first_device)
self.wpe = self.wpe.to(self.first_device)
# Load onto devices
for k, v in self.device_map.items():
for block in v:
cuda_device = "cuda:" + str(k)
self.h[block] = self.h[block].to(cuda_device)
# ln_f to last
self.ln_f = self.ln_f.to(self.last_device)
def deparallelize(self):
self.model_parallel = False
self.device_map = None
self.first_device = "cpu"
self.last_device = "cpu"
self.wte = self.wte.to("cpu")
self.wpe = self.wpe.to("cpu")
for index in range(len(self.h)):
self.h[index] = self.h[index].to("cpu")
self.ln_f = self.ln_f.to("cpu")
torch.cuda.empty_cache()
def get_input_embeddings(self):
return self.wte
def set_input_embeddings(self, new_embeddings):
self.wte = new_embeddings
def _prune_heads(self, heads_to_prune):
"""
Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer}
"""
for layer, heads in heads_to_prune.items():
self.h[layer].attn.prune_heads(heads)
def forward(
self,
input_ids=None,
kg_masks=None, # Required new parameter for the kg masks.
past_key_values=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
encoder_hidden_states=None,
encoder_attention_mask=None,
use_cache=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
output_hidden_states = (
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
)
use_cache = use_cache if use_cache is not None else self.config.use_cache
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
if input_ids is not None and inputs_embeds is not None:
raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
elif input_ids is not None:
input_shape = input_ids.size()
input_ids = input_ids.view(-1, input_shape[-1])
batch_size = input_ids.shape[0]
elif inputs_embeds is not None:
input_shape = inputs_embeds.size()[:-1]
batch_size = inputs_embeds.shape[0]
else:
raise ValueError("You have to specify either input_ids or inputs_embeds")
if token_type_ids is not None:
token_type_ids = token_type_ids.view(-1, input_shape[-1])
if position_ids is not None:
position_ids = position_ids.view(-1, input_shape[-1])
if past_key_values is None:
past_length = 0
past_key_values = tuple([None] * len(self.h))
else:
past_length = past_key_values[0][0].size(-2)
if position_ids is None:
device = input_ids.device if input_ids is not None else inputs_embeds.device
position_ids = torch.arange(past_length, input_shape[-1] + past_length, dtype=torch.long, device=device)
position_ids = position_ids.unsqueeze(0).view(-1, input_shape[-1])
# Attention mask.
if attention_mask is not None:
assert batch_size > 0, "batch_size has to be defined and > 0"
attention_mask = attention_mask.view(batch_size, -1)
# We create a 3D attention mask from a 2D tensor mask.
# Sizes are [batch_size, 1, 1, to_seq_length]
# So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length]
# this attention mask is more simple than the triangular masking of causal attention
# used in OpenAI GPT, we just need to prepare the broadcast dimension here.
attention_mask = attention_mask[:, None, None, :]
# Since attention_mask is 1.0 for positions we want to attend and 0.0 for
# masked positions, this operation will create a tensor which is 0.0 for
# positions we want to attend and -10000.0 for masked positions.
# Since we are adding it to the raw scores before the softmax, this is
# effectively the same as removing these entirely.
attention_mask = attention_mask.to(dtype=self.dtype) # fp16 compatibility
attention_mask = (1.0 - attention_mask) * -10000.0
# If a 2D ou 3D attention mask is provided for the cross-attention
# we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
if self.config.add_cross_attention and encoder_hidden_states is not None:
encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
if encoder_attention_mask is None:
encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)
encoder_attention_mask = self.invert_attention_mask(encoder_attention_mask)
else:
encoder_attention_mask = None
# Prepare head mask if needed
# 1.0 in head_mask indicate we keep the head
# attention_probs has shape bsz x n_heads x N x N
# head_mask has shape n_layer x batch x n_heads x N x N
head_mask = self.get_head_mask(head_mask, self.config.n_layer)
if inputs_embeds is None:
inputs_embeds = self.wte(input_ids)
position_embeds = self.wpe(position_ids)
hidden_states = inputs_embeds + position_embeds
if token_type_ids is not None:
token_type_embeds = self.wte(token_type_ids)
hidden_states = hidden_states + token_type_embeds
hidden_states = self.drop(hidden_states)
output_shape = input_shape + (hidden_states.size(-1),)
presents = () if use_cache else None
all_self_attentions = () if output_attentions else None
all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
all_hidden_states = () if output_hidden_states else None
for i, (block, layer_past) in enumerate(zip(self.h, past_key_values)):
# Model parallel
if self.model_parallel:
torch.cuda.set_device(hidden_states.device)
# Ensure layer_past is on same device as hidden_states (might not be correct)
if layer_past is not None:
layer_past = tuple(past_state.to(hidden_states.device) for past_state in layer_past)
# Ensure that attention_mask is always on the same device as hidden_states
if attention_mask is not None:
attention_mask = attention_mask.to(hidden_states.device)
if isinstance(head_mask, torch.Tensor):
head_mask = head_mask.to(hidden_states.device)
if output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_states,)
if getattr(self.config, "gradient_checkpointing", False) and self.training:
if use_cache:
logger.warn(
"`use_cache=True` is incompatible with `config.gradient_checkpointing=True`. Setting "
"`use_cache=False`..."
)
use_cache = False
def create_custom_forward(module):
def custom_forward(*inputs):
# None for past_key_value
return module(*inputs, use_cache, output_attentions)
return custom_forward
outputs = torch.utils.checkpoint.checkpoint(
create_custom_forward(block),
hidden_states,
None,
attention_mask,
head_mask[i],
encoder_hidden_states,
encoder_attention_mask,
)
else:
outputs = block(
hidden_states,
kg_masks=kg_masks,
layer_past=layer_past,
attention_mask=attention_mask,
head_mask=head_mask[i],
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
use_cache=use_cache,
output_attentions=output_attentions,
)
hidden_states = outputs[0]
if use_cache is True:
presents = presents + (outputs[1],)
if output_attentions:
all_self_attentions = all_self_attentions + (outputs[2 if use_cache else 1],)
if self.config.add_cross_attention:
all_cross_attentions = all_cross_attentions + (outputs[3 if use_cache else 2],)
# Model Parallel: If it's the last layer for that device, put things on the next device
if self.model_parallel:
for k, v in self.device_map.items():
if i == v[-1] and "cuda:" + str(k) != self.last_device:
hidden_states = hidden_states.to("cuda:" + str(k + 1))
hidden_states = self.ln_f(hidden_states)
hidden_states = hidden_states.view(*output_shape)
# Add last hidden state
if output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_states,)
if not return_dict:
return tuple(v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None)
return BaseModelOutputWithPastAndCrossAttentions(
last_hidden_state=hidden_states,
past_key_values=presents,
hidden_states=all_hidden_states,
attentions=all_self_attentions,
cross_attentions=all_cross_attentions,
)
#######################################################################################################################
# GPT2 LM Head Class #
#######################################################################################################################
class GPT2LMHeadModel(GPT2PreTrainedModel):
_keys_to_ignore_on_load_missing = [r"h\.\d+\.attn\.masked_bias", r"lm_head\.weight"]
def __init__(self, config):
super().__init__(config)
self.transformer = GPT2Model(config)
self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
self.init_weights()
# Model parallel
self.model_parallel = False
self.device_map = None
def parallelize(self, device_map=None):
self.device_map = (
get_device_map(len(self.transformer.h), range(torch.cuda.device_count()))
if device_map is None
else device_map
)
assert_device_map(self.device_map, len(self.transformer.h))
self.transformer.parallelize(self.device_map)
self.lm_head = self.lm_head.to(self.transformer.first_device)
self.model_parallel = True
def deparallelize(self):
self.transformer.deparallelize()
self.transformer = self.transformer.to("cpu")
self.lm_head = self.lm_head.to("cpu")
self.model_parallel = False
torch.cuda.empty_cache()
def get_output_embeddings(self):
return self.lm_head
def set_output_embeddings(self, new_embeddings):
self.lm_head = new_embeddings
def prepare_inputs_for_generation(self, input_ids, past=None, **kwargs):
token_type_ids = kwargs.get("token_type_ids", None)
# only last token for inputs_ids if past is defined in kwargs
if past:
input_ids = input_ids[:, -1].unsqueeze(-1)
if token_type_ids is not None:
token_type_ids = token_type_ids[:, -1].unsqueeze(-1)
attention_mask = kwargs.get("attention_mask", None)
position_ids = kwargs.get("position_ids", None)
if attention_mask is not None and position_ids is None:
# create position_ids on the fly for batch generation
position_ids = attention_mask.long().cumsum(-1) - 1
position_ids.masked_fill_(attention_mask == 0, 1)
if past:
position_ids = position_ids[:, -1].unsqueeze(-1)
else:
position_ids = None
return {
"input_ids": input_ids,
"past_key_values": past,
"use_cache": kwargs.get("use_cache"),
"position_ids": position_ids,
"attention_mask": attention_mask,
"token_type_ids": token_type_ids,
}
def forward(
self,
input_ids=None,
kg_masks=None, # Parameter added by authors. Simply forwarded to GPTModel
past_key_values=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
encoder_hidden_states=None,
encoder_attention_mask=None,
labels=None,
use_cache=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
``labels = input_ids`` Indices are selected in ``[-100, 0, ..., config.vocab_size]`` All labels set to
``-100`` are ignored (masked), the loss is only computed for labels in ``[0, ..., config.vocab_size]``
"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
transformer_outputs = self.transformer(
input_ids,
kg_masks=kg_masks, # forwarded here
past_key_values=past_key_values,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
encoder_hidden_states=encoder_hidden_states,
encoder_attention_mask=encoder_attention_mask,
use_cache=use_cache,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
hidden_states = transformer_outputs[0]
# Set device for model parallelism
if self.model_parallel:
torch.cuda.set_device(self.transformer.first_device)
hidden_states = hidden_states.to(self.lm_head.weight.device)
lm_logits = self.lm_head(hidden_states)
loss = None
if labels is not None:
# Shift so that tokens < n predict n
shift_logits = lm_logits[..., :-1, :].contiguous()
shift_labels = labels[..., 1:].contiguous()
# Flatten the tokens
loss_fct = CrossEntropyLoss()
loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
if not return_dict:
output = (lm_logits,) + transformer_outputs[1:]
return ((loss,) + output) if loss is not None else output
return CausalLMOutputWithCrossAttentions(
loss=loss,
logits=lm_logits,
past_key_values=transformer_outputs.past_key_values,
hidden_states=transformer_outputs.hidden_states,
attentions=transformer_outputs.attentions,
cross_attentions=transformer_outputs.cross_attentions,
)
@staticmethod
def _reorder_cache(past: Tuple[Tuple[torch.Tensor]], beam_idx: torch.Tensor) -> Tuple[Tuple[torch.Tensor]]:
"""
This function is used to re-order the :obj:`past_key_values` cache if
:meth:`~transformers.PreTrainedModel.beam_search` or :meth:`~transformers.PreTrainedModel.beam_sample` is
called. This is required to match :obj:`past_key_values` with the correct beam_idx at every generation step.
"""
return tuple(
tuple(past_state.index_select(0, beam_idx.to(past_state.device)) for past_state in layer_past)
for layer_past in past
)