File size: 14,208 Bytes
4c65bff |
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 |
# coding=utf-8
# Copyright 2018 The Google Flax Team Authors and The HuggingFace Inc. team.
#
# 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.
""" Auto Model class."""
from collections import OrderedDict
from ...utils import logging
from .auto_factory import _BaseAutoModelClass, _LazyAutoMapping, auto_class_update
from .configuration_auto import CONFIG_MAPPING_NAMES
logger = logging.get_logger(__name__)
FLAX_MODEL_MAPPING_NAMES = OrderedDict(
[
# Base model mapping
("albert", "FlaxAlbertModel"),
("bart", "FlaxBartModel"),
("beit", "FlaxBeitModel"),
("bert", "FlaxBertModel"),
("big_bird", "FlaxBigBirdModel"),
("blenderbot", "FlaxBlenderbotModel"),
("blenderbot-small", "FlaxBlenderbotSmallModel"),
("bloom", "FlaxBloomModel"),
("clip", "FlaxCLIPModel"),
("distilbert", "FlaxDistilBertModel"),
("electra", "FlaxElectraModel"),
("gpt-sw3", "FlaxGPT2Model"),
("gpt2", "FlaxGPT2Model"),
("gpt_neo", "FlaxGPTNeoModel"),
("gptj", "FlaxGPTJModel"),
("longt5", "FlaxLongT5Model"),
("marian", "FlaxMarianModel"),
("mbart", "FlaxMBartModel"),
("mt5", "FlaxMT5Model"),
("opt", "FlaxOPTModel"),
("pegasus", "FlaxPegasusModel"),
("regnet", "FlaxRegNetModel"),
("resnet", "FlaxResNetModel"),
("roberta", "FlaxRobertaModel"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormModel"),
("roformer", "FlaxRoFormerModel"),
("t5", "FlaxT5Model"),
("vision-text-dual-encoder", "FlaxVisionTextDualEncoderModel"),
("vit", "FlaxViTModel"),
("wav2vec2", "FlaxWav2Vec2Model"),
("whisper", "FlaxWhisperModel"),
("xglm", "FlaxXGLMModel"),
("xlm-roberta", "FlaxXLMRobertaModel"),
]
)
FLAX_MODEL_FOR_PRETRAINING_MAPPING_NAMES = OrderedDict(
[
# Model for pre-training mapping
("albert", "FlaxAlbertForPreTraining"),
("bart", "FlaxBartForConditionalGeneration"),
("bert", "FlaxBertForPreTraining"),
("big_bird", "FlaxBigBirdForPreTraining"),
("electra", "FlaxElectraForPreTraining"),
("longt5", "FlaxLongT5ForConditionalGeneration"),
("mbart", "FlaxMBartForConditionalGeneration"),
("mt5", "FlaxMT5ForConditionalGeneration"),
("roberta", "FlaxRobertaForMaskedLM"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForMaskedLM"),
("roformer", "FlaxRoFormerForMaskedLM"),
("t5", "FlaxT5ForConditionalGeneration"),
("wav2vec2", "FlaxWav2Vec2ForPreTraining"),
("whisper", "FlaxWhisperForConditionalGeneration"),
("xlm-roberta", "FlaxXLMRobertaForMaskedLM"),
]
)
FLAX_MODEL_FOR_MASKED_LM_MAPPING_NAMES = OrderedDict(
[
# Model for Masked LM mapping
("albert", "FlaxAlbertForMaskedLM"),
("bart", "FlaxBartForConditionalGeneration"),
("bert", "FlaxBertForMaskedLM"),
("big_bird", "FlaxBigBirdForMaskedLM"),
("distilbert", "FlaxDistilBertForMaskedLM"),
("electra", "FlaxElectraForMaskedLM"),
("mbart", "FlaxMBartForConditionalGeneration"),
("roberta", "FlaxRobertaForMaskedLM"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForMaskedLM"),
("roformer", "FlaxRoFormerForMaskedLM"),
("xlm-roberta", "FlaxXLMRobertaForMaskedLM"),
]
)
FLAX_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMES = OrderedDict(
[
# Model for Seq2Seq Causal LM mapping
("bart", "FlaxBartForConditionalGeneration"),
("blenderbot", "FlaxBlenderbotForConditionalGeneration"),
("blenderbot-small", "FlaxBlenderbotSmallForConditionalGeneration"),
("encoder-decoder", "FlaxEncoderDecoderModel"),
("longt5", "FlaxLongT5ForConditionalGeneration"),
("marian", "FlaxMarianMTModel"),
("mbart", "FlaxMBartForConditionalGeneration"),
("mt5", "FlaxMT5ForConditionalGeneration"),
("pegasus", "FlaxPegasusForConditionalGeneration"),
("t5", "FlaxT5ForConditionalGeneration"),
]
)
FLAX_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES = OrderedDict(
[
# Model for Image-classsification
("beit", "FlaxBeitForImageClassification"),
("regnet", "FlaxRegNetForImageClassification"),
("resnet", "FlaxResNetForImageClassification"),
("vit", "FlaxViTForImageClassification"),
]
)
FLAX_MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES = OrderedDict(
[
("vision-encoder-decoder", "FlaxVisionEncoderDecoderModel"),
]
)
FLAX_MODEL_FOR_CAUSAL_LM_MAPPING_NAMES = OrderedDict(
[
# Model for Causal LM mapping
("bart", "FlaxBartForCausalLM"),
("bert", "FlaxBertForCausalLM"),
("big_bird", "FlaxBigBirdForCausalLM"),
("bloom", "FlaxBloomForCausalLM"),
("electra", "FlaxElectraForCausalLM"),
("gpt-sw3", "FlaxGPT2LMHeadModel"),
("gpt2", "FlaxGPT2LMHeadModel"),
("gpt_neo", "FlaxGPTNeoForCausalLM"),
("gptj", "FlaxGPTJForCausalLM"),
("opt", "FlaxOPTForCausalLM"),
("roberta", "FlaxRobertaForCausalLM"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForCausalLM"),
("xglm", "FlaxXGLMForCausalLM"),
("xlm-roberta", "FlaxXLMRobertaForCausalLM"),
]
)
FLAX_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING_NAMES = OrderedDict(
[
# Model for Sequence Classification mapping
("albert", "FlaxAlbertForSequenceClassification"),
("bart", "FlaxBartForSequenceClassification"),
("bert", "FlaxBertForSequenceClassification"),
("big_bird", "FlaxBigBirdForSequenceClassification"),
("distilbert", "FlaxDistilBertForSequenceClassification"),
("electra", "FlaxElectraForSequenceClassification"),
("mbart", "FlaxMBartForSequenceClassification"),
("roberta", "FlaxRobertaForSequenceClassification"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForSequenceClassification"),
("roformer", "FlaxRoFormerForSequenceClassification"),
("xlm-roberta", "FlaxXLMRobertaForSequenceClassification"),
]
)
FLAX_MODEL_FOR_QUESTION_ANSWERING_MAPPING_NAMES = OrderedDict(
[
# Model for Question Answering mapping
("albert", "FlaxAlbertForQuestionAnswering"),
("bart", "FlaxBartForQuestionAnswering"),
("bert", "FlaxBertForQuestionAnswering"),
("big_bird", "FlaxBigBirdForQuestionAnswering"),
("distilbert", "FlaxDistilBertForQuestionAnswering"),
("electra", "FlaxElectraForQuestionAnswering"),
("mbart", "FlaxMBartForQuestionAnswering"),
("roberta", "FlaxRobertaForQuestionAnswering"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForQuestionAnswering"),
("roformer", "FlaxRoFormerForQuestionAnswering"),
("xlm-roberta", "FlaxXLMRobertaForQuestionAnswering"),
]
)
FLAX_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMES = OrderedDict(
[
# Model for Token Classification mapping
("albert", "FlaxAlbertForTokenClassification"),
("bert", "FlaxBertForTokenClassification"),
("big_bird", "FlaxBigBirdForTokenClassification"),
("distilbert", "FlaxDistilBertForTokenClassification"),
("electra", "FlaxElectraForTokenClassification"),
("roberta", "FlaxRobertaForTokenClassification"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForTokenClassification"),
("roformer", "FlaxRoFormerForTokenClassification"),
("xlm-roberta", "FlaxXLMRobertaForTokenClassification"),
]
)
FLAX_MODEL_FOR_MULTIPLE_CHOICE_MAPPING_NAMES = OrderedDict(
[
# Model for Multiple Choice mapping
("albert", "FlaxAlbertForMultipleChoice"),
("bert", "FlaxBertForMultipleChoice"),
("big_bird", "FlaxBigBirdForMultipleChoice"),
("distilbert", "FlaxDistilBertForMultipleChoice"),
("electra", "FlaxElectraForMultipleChoice"),
("roberta", "FlaxRobertaForMultipleChoice"),
("roberta-prelayernorm", "FlaxRobertaPreLayerNormForMultipleChoice"),
("roformer", "FlaxRoFormerForMultipleChoice"),
("xlm-roberta", "FlaxXLMRobertaForMultipleChoice"),
]
)
FLAX_MODEL_FOR_NEXT_SENTENCE_PREDICTION_MAPPING_NAMES = OrderedDict(
[
("bert", "FlaxBertForNextSentencePrediction"),
]
)
FLAX_MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES = OrderedDict(
[
("speech-encoder-decoder", "FlaxSpeechEncoderDecoderModel"),
("whisper", "FlaxWhisperForConditionalGeneration"),
]
)
FLAX_MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES = OrderedDict(
[
("whisper", "FlaxWhisperForAudioClassification"),
]
)
FLAX_MODEL_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, FLAX_MODEL_MAPPING_NAMES)
FLAX_MODEL_FOR_PRETRAINING_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_PRETRAINING_MAPPING_NAMES)
FLAX_MODEL_FOR_MASKED_LM_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_MASKED_LM_MAPPING_NAMES)
FLAX_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMES
)
FLAX_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES
)
FLAX_MODEL_FOR_VISION_2_SEQ_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES)
FLAX_MODEL_FOR_CAUSAL_LM_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)
FLAX_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING_NAMES
)
FLAX_MODEL_FOR_QUESTION_ANSWERING_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_QUESTION_ANSWERING_MAPPING_NAMES
)
FLAX_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMES
)
FLAX_MODEL_FOR_MULTIPLE_CHOICE_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_MULTIPLE_CHOICE_MAPPING_NAMES
)
FLAX_MODEL_FOR_NEXT_SENTENCE_PREDICTION_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_NEXT_SENTENCE_PREDICTION_MAPPING_NAMES
)
FLAX_MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES
)
FLAX_MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING = _LazyAutoMapping(
CONFIG_MAPPING_NAMES, FLAX_MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES
)
class FlaxAutoModel(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_MAPPING
FlaxAutoModel = auto_class_update(FlaxAutoModel)
class FlaxAutoModelForPreTraining(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_PRETRAINING_MAPPING
FlaxAutoModelForPreTraining = auto_class_update(FlaxAutoModelForPreTraining, head_doc="pretraining")
class FlaxAutoModelForCausalLM(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_CAUSAL_LM_MAPPING
FlaxAutoModelForCausalLM = auto_class_update(FlaxAutoModelForCausalLM, head_doc="causal language modeling")
class FlaxAutoModelForMaskedLM(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_MASKED_LM_MAPPING
FlaxAutoModelForMaskedLM = auto_class_update(FlaxAutoModelForMaskedLM, head_doc="masked language modeling")
class FlaxAutoModelForSeq2SeqLM(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING
FlaxAutoModelForSeq2SeqLM = auto_class_update(
FlaxAutoModelForSeq2SeqLM, head_doc="sequence-to-sequence language modeling", checkpoint_for_example="t5-base"
)
class FlaxAutoModelForSequenceClassification(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING
FlaxAutoModelForSequenceClassification = auto_class_update(
FlaxAutoModelForSequenceClassification, head_doc="sequence classification"
)
class FlaxAutoModelForQuestionAnswering(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_QUESTION_ANSWERING_MAPPING
FlaxAutoModelForQuestionAnswering = auto_class_update(FlaxAutoModelForQuestionAnswering, head_doc="question answering")
class FlaxAutoModelForTokenClassification(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING
FlaxAutoModelForTokenClassification = auto_class_update(
FlaxAutoModelForTokenClassification, head_doc="token classification"
)
class FlaxAutoModelForMultipleChoice(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_MULTIPLE_CHOICE_MAPPING
FlaxAutoModelForMultipleChoice = auto_class_update(FlaxAutoModelForMultipleChoice, head_doc="multiple choice")
class FlaxAutoModelForNextSentencePrediction(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_NEXT_SENTENCE_PREDICTION_MAPPING
FlaxAutoModelForNextSentencePrediction = auto_class_update(
FlaxAutoModelForNextSentencePrediction, head_doc="next sentence prediction"
)
class FlaxAutoModelForImageClassification(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING
FlaxAutoModelForImageClassification = auto_class_update(
FlaxAutoModelForImageClassification, head_doc="image classification"
)
class FlaxAutoModelForVision2Seq(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_VISION_2_SEQ_MAPPING
FlaxAutoModelForVision2Seq = auto_class_update(FlaxAutoModelForVision2Seq, head_doc="vision-to-text modeling")
class FlaxAutoModelForSpeechSeq2Seq(_BaseAutoModelClass):
_model_mapping = FLAX_MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING
FlaxAutoModelForSpeechSeq2Seq = auto_class_update(
FlaxAutoModelForSpeechSeq2Seq, head_doc="sequence-to-sequence speech-to-text modeling"
)
|