File size: 41,961 Bytes
1ce5e18 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 |
# Copyright 2021 The HuggingFace Team. 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.
from typing import Dict, Optional, Tuple
import flax
import jax.numpy as jnp
from .utils import ModelOutput
@flax.struct.dataclass
class FlaxBaseModelOutput(ModelOutput):
"""
Base class for model's outputs, with potential hidden states and attentions.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
last_hidden_state: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxBaseModelOutputWithNoAttention(ModelOutput):
"""
Base class for model's outputs, with potential hidden states.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, num_channels, height, width)`):
Sequence of hidden-states at the output of the last layer of the model.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings, if the model has an embedding layer, + one
for the output of each layer) of shape `(batch_size, num_channels, height, width)`. Hidden-states of the
model at the output of each layer plus the optional initial embedding outputs.
"""
last_hidden_state: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxBaseModelOutputWithPoolingAndNoAttention(ModelOutput):
"""
Base class for model's outputs that also contains a pooling of the last hidden states.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, num_channels, height, width)`):
Sequence of hidden-states at the output of the last layer of the model.
pooler_output (`jnp.ndarray` of shape `(batch_size, hidden_size)`):
Last layer hidden-state after a pooling operation on the spatial dimensions.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings, if the model has an embedding layer, + one
for the output of each layer) of shape `(batch_size, num_channels, height, width)`. Hidden-states of the
model at the output of each layer plus the optional initial embedding outputs.
"""
last_hidden_state: jnp.ndarray = None
pooler_output: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxImageClassifierOutputWithNoAttention(ModelOutput):
"""
Base class for outputs of image classification models.
Args:
logits (`jnp.ndarray` of shape `(batch_size, config.num_labels)`):
Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when
`config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings, if the model has an embedding layer, + one
for the output of each stage) of shape `(batch_size, num_channels, height, width)`. Hidden-states (also
called feature maps) of the model at the output of each stage.
"""
logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxBaseModelOutputWithPast(ModelOutput):
"""
Base class for model's outputs, with potential hidden states and attentions.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
past_key_values (`Dict[str, jnp.ndarray]`):
Dictionary of pre-computed hidden-states (key and values in the attention blocks) that can be used for fast
auto-regressive decoding. Pre-computed key and value hidden-states are of shape *[batch_size, max_length]*.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
last_hidden_state: jnp.ndarray = None
past_key_values: Optional[Dict[str, jnp.ndarray]] = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxBaseModelOutputWithPooling(ModelOutput):
"""
Base class for model's outputs that also contains a pooling of the last hidden states.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
pooler_output (`jnp.ndarray` of shape `(batch_size, hidden_size)`):
Last layer hidden-state of the first token of the sequence (classification token) further processed by a
Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence
prediction (classification) objective during pretraining.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
last_hidden_state: jnp.ndarray = None
pooler_output: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxBaseModelOutputWithPoolingAndCrossAttentions(ModelOutput):
"""
Base class for model's outputs that also contains a pooling of the last hidden states.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
pooler_output (`jnp.ndarray` of shape `(batch_size, hidden_size)`):
Last layer hidden-state of the first token of the sequence (classification token) after further processing
through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns
the classification token after processing through a linear layer and a tanh activation function. The linear
layer weights are trained from the next sentence prediction (classification) objective during pretraining.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings, if the model has an embedding layer, + one
for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
weighted average in the cross-attention heads.
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if
`config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads,
encoder_sequence_length, embed_size_per_head)`.
Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
`config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values`
input) to speed up sequential decoding.
"""
last_hidden_state: jnp.ndarray = None
pooler_output: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxBaseModelOutputWithPastAndCrossAttentions(ModelOutput):
"""
Base class for model's outputs that may also contain a past key/values (to speed up sequential decoding).
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
hidden_size)` is output.
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if
`config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads,
encoder_sequence_length, embed_size_per_head)`.
Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
`config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values`
input) to speed up sequential decoding.
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
weighted average in the cross-attention heads.
"""
last_hidden_state: jnp.ndarray = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxSeq2SeqModelOutput(ModelOutput):
"""
Base class for model encoder's outputs that also contains : pre-computed hidden states that can speed up sequential
decoding.
Args:
last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the decoder of the model.
If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
hidden_size)` is output.
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
`(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.
Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
decoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
weighted average in the cross-attention heads.
encoder_last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder of the model.
encoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
encoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
"""
last_hidden_state: jnp.ndarray = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
decoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
decoder_attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
encoder_last_hidden_state: Optional[jnp.ndarray] = None
encoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
encoder_attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxCausalLMOutputWithCrossAttentions(ModelOutput):
"""
Base class for causal language model (or autoregressive) outputs.
Args:
logits (`jnp.ndarray` of shape `(batch_size, sequence_length, config.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Cross attentions weights after the attention softmax, used to compute the weighted average in the
cross-attention heads.
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `jnp.ndarray` tuples of length `config.n_layers`, with each tuple containing the cached key, value
states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting.
Only relevant if `config.is_decoder = True`.
Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
`past_key_values` input) to speed up sequential decoding.
"""
logits: jnp.ndarray = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxMaskedLMOutput(ModelOutput):
"""
Base class for masked language models outputs.
Args:
logits (`jnp.ndarray` of shape `(batch_size, sequence_length, config.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
FlaxCausalLMOutput = FlaxMaskedLMOutput
@flax.struct.dataclass
class FlaxSeq2SeqLMOutput(ModelOutput):
"""
Base class for sequence-to-sequence language models outputs.
Args:
logits (`jnp.ndarray` of shape `(batch_size, sequence_length, config.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
`(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.
Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
decoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
weighted average in the cross-attention heads.
encoder_last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder of the model.
encoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
encoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
"""
logits: jnp.ndarray = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
decoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
decoder_attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
encoder_last_hidden_state: Optional[jnp.ndarray] = None
encoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
encoder_attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxNextSentencePredictorOutput(ModelOutput):
"""
Base class for outputs of models predicting if two sentences are consecutive or not.
Args:
logits (`jnp.ndarray` of shape `(batch_size, 2)`):
Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation
before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxSequenceClassifierOutput(ModelOutput):
"""
Base class for outputs of sentence classification models.
Args:
logits (`jnp.ndarray` of shape `(batch_size, config.num_labels)`):
Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxSeq2SeqSequenceClassifierOutput(ModelOutput):
"""
Base class for outputs of sequence-to-sequence sentence classification models.
Args:
logits (`jnp.ndarray` of shape `(batch_size, config.num_labels)`):
Classification (or regression if config.num_labels==1) scores (before SoftMax).
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
`(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.
Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
decoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
weighted average in the cross-attention heads.
encoder_last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder of the model.
encoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
encoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
"""
logits: jnp.ndarray = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
decoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
decoder_attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
encoder_last_hidden_state: Optional[jnp.ndarray] = None
encoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
encoder_attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxMultipleChoiceModelOutput(ModelOutput):
"""
Base class for outputs of multiple choice models.
Args:
logits (`jnp.ndarray` of shape `(batch_size, num_choices)`):
*num_choices* is the second dimension of the input tensors. (see *input_ids* above).
Classification scores (before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxTokenClassifierOutput(ModelOutput):
"""
Base class for outputs of token classification models.
Args:
logits (`jnp.ndarray` of shape `(batch_size, sequence_length, config.num_labels)`):
Classification scores (before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxQuestionAnsweringModelOutput(ModelOutput):
"""
Base class for outputs of question answering models.
Args:
start_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`):
Span-start scores (before SoftMax).
end_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`):
Span-end scores (before SoftMax).
hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
start_logits: jnp.ndarray = None
end_logits: jnp.ndarray = None
hidden_states: Optional[Tuple[jnp.ndarray]] = None
attentions: Optional[Tuple[jnp.ndarray]] = None
@flax.struct.dataclass
class FlaxSeq2SeqQuestionAnsweringModelOutput(ModelOutput):
"""
Base class for outputs of sequence-to-sequence question answering models.
Args:
start_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`):
Span-start scores (before SoftMax).
end_logits (`jnp.ndarray` of shape `(batch_size, sequence_length)`):
Span-end scores (before SoftMax).
past_key_values (`tuple(tuple(jnp.ndarray))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(jnp.ndarray)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
`(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.
Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
decoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
decoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
cross_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
weighted average in the cross-attention heads.
encoder_last_hidden_state (`jnp.ndarray` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder of the model.
encoder_hidden_states (`tuple(jnp.ndarray)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `jnp.ndarray` (one for the output of the embeddings + one for the output of each layer) of shape
`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
encoder_attentions (`tuple(jnp.ndarray)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `jnp.ndarray` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
self-attention heads.
"""
start_logits: jnp.ndarray = None
end_logits: jnp.ndarray = None
past_key_values: Optional[Tuple[Tuple[jnp.ndarray]]] = None
decoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
decoder_attentions: Optional[Tuple[jnp.ndarray]] = None
cross_attentions: Optional[Tuple[jnp.ndarray]] = None
encoder_last_hidden_state: Optional[jnp.ndarray] = None
encoder_hidden_states: Optional[Tuple[jnp.ndarray]] = None
encoder_attentions: Optional[Tuple[jnp.ndarray]] = None
|