keras-hub-nightly 0.15.0.dev20240823171555__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- keras_hub/__init__.py +52 -0
- keras_hub/api/__init__.py +27 -0
- keras_hub/api/layers/__init__.py +47 -0
- keras_hub/api/metrics/__init__.py +24 -0
- keras_hub/api/models/__init__.py +249 -0
- keras_hub/api/samplers/__init__.py +29 -0
- keras_hub/api/tokenizers/__init__.py +35 -0
- keras_hub/src/__init__.py +13 -0
- keras_hub/src/api_export.py +53 -0
- keras_hub/src/layers/__init__.py +13 -0
- keras_hub/src/layers/modeling/__init__.py +13 -0
- keras_hub/src/layers/modeling/alibi_bias.py +143 -0
- keras_hub/src/layers/modeling/cached_multi_head_attention.py +137 -0
- keras_hub/src/layers/modeling/f_net_encoder.py +200 -0
- keras_hub/src/layers/modeling/masked_lm_head.py +239 -0
- keras_hub/src/layers/modeling/position_embedding.py +123 -0
- keras_hub/src/layers/modeling/reversible_embedding.py +311 -0
- keras_hub/src/layers/modeling/rotary_embedding.py +169 -0
- keras_hub/src/layers/modeling/sine_position_encoding.py +108 -0
- keras_hub/src/layers/modeling/token_and_position_embedding.py +150 -0
- keras_hub/src/layers/modeling/transformer_decoder.py +496 -0
- keras_hub/src/layers/modeling/transformer_encoder.py +262 -0
- keras_hub/src/layers/modeling/transformer_layer_utils.py +106 -0
- keras_hub/src/layers/preprocessing/__init__.py +13 -0
- keras_hub/src/layers/preprocessing/masked_lm_mask_generator.py +220 -0
- keras_hub/src/layers/preprocessing/multi_segment_packer.py +319 -0
- keras_hub/src/layers/preprocessing/preprocessing_layer.py +62 -0
- keras_hub/src/layers/preprocessing/random_deletion.py +271 -0
- keras_hub/src/layers/preprocessing/random_swap.py +267 -0
- keras_hub/src/layers/preprocessing/start_end_packer.py +219 -0
- keras_hub/src/metrics/__init__.py +13 -0
- keras_hub/src/metrics/bleu.py +394 -0
- keras_hub/src/metrics/edit_distance.py +197 -0
- keras_hub/src/metrics/perplexity.py +181 -0
- keras_hub/src/metrics/rouge_base.py +204 -0
- keras_hub/src/metrics/rouge_l.py +97 -0
- keras_hub/src/metrics/rouge_n.py +125 -0
- keras_hub/src/models/__init__.py +13 -0
- keras_hub/src/models/albert/__init__.py +20 -0
- keras_hub/src/models/albert/albert_backbone.py +267 -0
- keras_hub/src/models/albert/albert_classifier.py +202 -0
- keras_hub/src/models/albert/albert_masked_lm.py +129 -0
- keras_hub/src/models/albert/albert_masked_lm_preprocessor.py +194 -0
- keras_hub/src/models/albert/albert_preprocessor.py +206 -0
- keras_hub/src/models/albert/albert_presets.py +70 -0
- keras_hub/src/models/albert/albert_tokenizer.py +119 -0
- keras_hub/src/models/backbone.py +311 -0
- keras_hub/src/models/bart/__init__.py +20 -0
- keras_hub/src/models/bart/bart_backbone.py +261 -0
- keras_hub/src/models/bart/bart_preprocessor.py +276 -0
- keras_hub/src/models/bart/bart_presets.py +74 -0
- keras_hub/src/models/bart/bart_seq_2_seq_lm.py +490 -0
- keras_hub/src/models/bart/bart_seq_2_seq_lm_preprocessor.py +262 -0
- keras_hub/src/models/bart/bart_tokenizer.py +124 -0
- keras_hub/src/models/bert/__init__.py +23 -0
- keras_hub/src/models/bert/bert_backbone.py +227 -0
- keras_hub/src/models/bert/bert_classifier.py +183 -0
- keras_hub/src/models/bert/bert_masked_lm.py +131 -0
- keras_hub/src/models/bert/bert_masked_lm_preprocessor.py +198 -0
- keras_hub/src/models/bert/bert_preprocessor.py +184 -0
- keras_hub/src/models/bert/bert_presets.py +147 -0
- keras_hub/src/models/bert/bert_tokenizer.py +112 -0
- keras_hub/src/models/bloom/__init__.py +20 -0
- keras_hub/src/models/bloom/bloom_attention.py +186 -0
- keras_hub/src/models/bloom/bloom_backbone.py +173 -0
- keras_hub/src/models/bloom/bloom_causal_lm.py +298 -0
- keras_hub/src/models/bloom/bloom_causal_lm_preprocessor.py +176 -0
- keras_hub/src/models/bloom/bloom_decoder.py +206 -0
- keras_hub/src/models/bloom/bloom_preprocessor.py +185 -0
- keras_hub/src/models/bloom/bloom_presets.py +121 -0
- keras_hub/src/models/bloom/bloom_tokenizer.py +116 -0
- keras_hub/src/models/causal_lm.py +383 -0
- keras_hub/src/models/classifier.py +109 -0
- keras_hub/src/models/csp_darknet/__init__.py +13 -0
- keras_hub/src/models/csp_darknet/csp_darknet_backbone.py +410 -0
- keras_hub/src/models/csp_darknet/csp_darknet_image_classifier.py +133 -0
- keras_hub/src/models/deberta_v3/__init__.py +24 -0
- keras_hub/src/models/deberta_v3/deberta_v3_backbone.py +210 -0
- keras_hub/src/models/deberta_v3/deberta_v3_classifier.py +228 -0
- keras_hub/src/models/deberta_v3/deberta_v3_masked_lm.py +135 -0
- keras_hub/src/models/deberta_v3/deberta_v3_masked_lm_preprocessor.py +191 -0
- keras_hub/src/models/deberta_v3/deberta_v3_preprocessor.py +206 -0
- keras_hub/src/models/deberta_v3/deberta_v3_presets.py +82 -0
- keras_hub/src/models/deberta_v3/deberta_v3_tokenizer.py +155 -0
- keras_hub/src/models/deberta_v3/disentangled_attention_encoder.py +227 -0
- keras_hub/src/models/deberta_v3/disentangled_self_attention.py +412 -0
- keras_hub/src/models/deberta_v3/relative_embedding.py +94 -0
- keras_hub/src/models/densenet/__init__.py +13 -0
- keras_hub/src/models/densenet/densenet_backbone.py +210 -0
- keras_hub/src/models/densenet/densenet_image_classifier.py +131 -0
- keras_hub/src/models/distil_bert/__init__.py +26 -0
- keras_hub/src/models/distil_bert/distil_bert_backbone.py +187 -0
- keras_hub/src/models/distil_bert/distil_bert_classifier.py +208 -0
- keras_hub/src/models/distil_bert/distil_bert_masked_lm.py +137 -0
- keras_hub/src/models/distil_bert/distil_bert_masked_lm_preprocessor.py +194 -0
- keras_hub/src/models/distil_bert/distil_bert_preprocessor.py +175 -0
- keras_hub/src/models/distil_bert/distil_bert_presets.py +57 -0
- keras_hub/src/models/distil_bert/distil_bert_tokenizer.py +114 -0
- keras_hub/src/models/electra/__init__.py +20 -0
- keras_hub/src/models/electra/electra_backbone.py +247 -0
- keras_hub/src/models/electra/electra_preprocessor.py +154 -0
- keras_hub/src/models/electra/electra_presets.py +95 -0
- keras_hub/src/models/electra/electra_tokenizer.py +104 -0
- keras_hub/src/models/f_net/__init__.py +20 -0
- keras_hub/src/models/f_net/f_net_backbone.py +236 -0
- keras_hub/src/models/f_net/f_net_classifier.py +154 -0
- keras_hub/src/models/f_net/f_net_masked_lm.py +132 -0
- keras_hub/src/models/f_net/f_net_masked_lm_preprocessor.py +196 -0
- keras_hub/src/models/f_net/f_net_preprocessor.py +177 -0
- keras_hub/src/models/f_net/f_net_presets.py +43 -0
- keras_hub/src/models/f_net/f_net_tokenizer.py +95 -0
- keras_hub/src/models/falcon/__init__.py +20 -0
- keras_hub/src/models/falcon/falcon_attention.py +156 -0
- keras_hub/src/models/falcon/falcon_backbone.py +164 -0
- keras_hub/src/models/falcon/falcon_causal_lm.py +291 -0
- keras_hub/src/models/falcon/falcon_causal_lm_preprocessor.py +173 -0
- keras_hub/src/models/falcon/falcon_preprocessor.py +187 -0
- keras_hub/src/models/falcon/falcon_presets.py +30 -0
- keras_hub/src/models/falcon/falcon_tokenizer.py +110 -0
- keras_hub/src/models/falcon/falcon_transformer_decoder.py +255 -0
- keras_hub/src/models/feature_pyramid_backbone.py +73 -0
- keras_hub/src/models/gemma/__init__.py +20 -0
- keras_hub/src/models/gemma/gemma_attention.py +250 -0
- keras_hub/src/models/gemma/gemma_backbone.py +316 -0
- keras_hub/src/models/gemma/gemma_causal_lm.py +448 -0
- keras_hub/src/models/gemma/gemma_causal_lm_preprocessor.py +167 -0
- keras_hub/src/models/gemma/gemma_decoder_block.py +241 -0
- keras_hub/src/models/gemma/gemma_preprocessor.py +191 -0
- keras_hub/src/models/gemma/gemma_presets.py +248 -0
- keras_hub/src/models/gemma/gemma_tokenizer.py +103 -0
- keras_hub/src/models/gemma/rms_normalization.py +40 -0
- keras_hub/src/models/gpt2/__init__.py +20 -0
- keras_hub/src/models/gpt2/gpt2_backbone.py +199 -0
- keras_hub/src/models/gpt2/gpt2_causal_lm.py +437 -0
- keras_hub/src/models/gpt2/gpt2_causal_lm_preprocessor.py +173 -0
- keras_hub/src/models/gpt2/gpt2_preprocessor.py +187 -0
- keras_hub/src/models/gpt2/gpt2_presets.py +82 -0
- keras_hub/src/models/gpt2/gpt2_tokenizer.py +110 -0
- keras_hub/src/models/gpt_neo_x/__init__.py +13 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_attention.py +251 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_backbone.py +175 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_causal_lm.py +201 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_causal_lm_preprocessor.py +141 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_decoder.py +258 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_preprocessor.py +145 -0
- keras_hub/src/models/gpt_neo_x/gpt_neo_x_tokenizer.py +88 -0
- keras_hub/src/models/image_classifier.py +90 -0
- keras_hub/src/models/llama/__init__.py +20 -0
- keras_hub/src/models/llama/llama_attention.py +225 -0
- keras_hub/src/models/llama/llama_backbone.py +188 -0
- keras_hub/src/models/llama/llama_causal_lm.py +327 -0
- keras_hub/src/models/llama/llama_causal_lm_preprocessor.py +170 -0
- keras_hub/src/models/llama/llama_decoder.py +246 -0
- keras_hub/src/models/llama/llama_layernorm.py +48 -0
- keras_hub/src/models/llama/llama_preprocessor.py +189 -0
- keras_hub/src/models/llama/llama_presets.py +80 -0
- keras_hub/src/models/llama/llama_tokenizer.py +84 -0
- keras_hub/src/models/llama3/__init__.py +20 -0
- keras_hub/src/models/llama3/llama3_backbone.py +84 -0
- keras_hub/src/models/llama3/llama3_causal_lm.py +46 -0
- keras_hub/src/models/llama3/llama3_causal_lm_preprocessor.py +173 -0
- keras_hub/src/models/llama3/llama3_preprocessor.py +21 -0
- keras_hub/src/models/llama3/llama3_presets.py +69 -0
- keras_hub/src/models/llama3/llama3_tokenizer.py +63 -0
- keras_hub/src/models/masked_lm.py +101 -0
- keras_hub/src/models/mistral/__init__.py +20 -0
- keras_hub/src/models/mistral/mistral_attention.py +238 -0
- keras_hub/src/models/mistral/mistral_backbone.py +203 -0
- keras_hub/src/models/mistral/mistral_causal_lm.py +328 -0
- keras_hub/src/models/mistral/mistral_causal_lm_preprocessor.py +175 -0
- keras_hub/src/models/mistral/mistral_layer_norm.py +48 -0
- keras_hub/src/models/mistral/mistral_preprocessor.py +190 -0
- keras_hub/src/models/mistral/mistral_presets.py +48 -0
- keras_hub/src/models/mistral/mistral_tokenizer.py +82 -0
- keras_hub/src/models/mistral/mistral_transformer_decoder.py +265 -0
- keras_hub/src/models/mix_transformer/__init__.py +13 -0
- keras_hub/src/models/mix_transformer/mix_transformer_backbone.py +181 -0
- keras_hub/src/models/mix_transformer/mix_transformer_classifier.py +133 -0
- keras_hub/src/models/mix_transformer/mix_transformer_layers.py +300 -0
- keras_hub/src/models/opt/__init__.py +20 -0
- keras_hub/src/models/opt/opt_backbone.py +173 -0
- keras_hub/src/models/opt/opt_causal_lm.py +301 -0
- keras_hub/src/models/opt/opt_causal_lm_preprocessor.py +177 -0
- keras_hub/src/models/opt/opt_preprocessor.py +188 -0
- keras_hub/src/models/opt/opt_presets.py +72 -0
- keras_hub/src/models/opt/opt_tokenizer.py +116 -0
- keras_hub/src/models/pali_gemma/__init__.py +23 -0
- keras_hub/src/models/pali_gemma/pali_gemma_backbone.py +277 -0
- keras_hub/src/models/pali_gemma/pali_gemma_causal_lm.py +313 -0
- keras_hub/src/models/pali_gemma/pali_gemma_causal_lm_preprocessor.py +147 -0
- keras_hub/src/models/pali_gemma/pali_gemma_decoder_block.py +160 -0
- keras_hub/src/models/pali_gemma/pali_gemma_presets.py +78 -0
- keras_hub/src/models/pali_gemma/pali_gemma_tokenizer.py +79 -0
- keras_hub/src/models/pali_gemma/pali_gemma_vit.py +566 -0
- keras_hub/src/models/phi3/__init__.py +20 -0
- keras_hub/src/models/phi3/phi3_attention.py +260 -0
- keras_hub/src/models/phi3/phi3_backbone.py +224 -0
- keras_hub/src/models/phi3/phi3_causal_lm.py +218 -0
- keras_hub/src/models/phi3/phi3_causal_lm_preprocessor.py +173 -0
- keras_hub/src/models/phi3/phi3_decoder.py +260 -0
- keras_hub/src/models/phi3/phi3_layernorm.py +48 -0
- keras_hub/src/models/phi3/phi3_preprocessor.py +190 -0
- keras_hub/src/models/phi3/phi3_presets.py +50 -0
- keras_hub/src/models/phi3/phi3_rotary_embedding.py +137 -0
- keras_hub/src/models/phi3/phi3_tokenizer.py +94 -0
- keras_hub/src/models/preprocessor.py +207 -0
- keras_hub/src/models/resnet/__init__.py +13 -0
- keras_hub/src/models/resnet/resnet_backbone.py +612 -0
- keras_hub/src/models/resnet/resnet_image_classifier.py +136 -0
- keras_hub/src/models/roberta/__init__.py +20 -0
- keras_hub/src/models/roberta/roberta_backbone.py +184 -0
- keras_hub/src/models/roberta/roberta_classifier.py +209 -0
- keras_hub/src/models/roberta/roberta_masked_lm.py +136 -0
- keras_hub/src/models/roberta/roberta_masked_lm_preprocessor.py +198 -0
- keras_hub/src/models/roberta/roberta_preprocessor.py +192 -0
- keras_hub/src/models/roberta/roberta_presets.py +43 -0
- keras_hub/src/models/roberta/roberta_tokenizer.py +132 -0
- keras_hub/src/models/seq_2_seq_lm.py +54 -0
- keras_hub/src/models/t5/__init__.py +20 -0
- keras_hub/src/models/t5/t5_backbone.py +261 -0
- keras_hub/src/models/t5/t5_layer_norm.py +35 -0
- keras_hub/src/models/t5/t5_multi_head_attention.py +324 -0
- keras_hub/src/models/t5/t5_presets.py +95 -0
- keras_hub/src/models/t5/t5_tokenizer.py +100 -0
- keras_hub/src/models/t5/t5_transformer_layer.py +178 -0
- keras_hub/src/models/task.py +419 -0
- keras_hub/src/models/vgg/__init__.py +13 -0
- keras_hub/src/models/vgg/vgg_backbone.py +158 -0
- keras_hub/src/models/vgg/vgg_image_classifier.py +124 -0
- keras_hub/src/models/vit_det/__init__.py +13 -0
- keras_hub/src/models/vit_det/vit_det_backbone.py +204 -0
- keras_hub/src/models/vit_det/vit_layers.py +565 -0
- keras_hub/src/models/whisper/__init__.py +20 -0
- keras_hub/src/models/whisper/whisper_audio_feature_extractor.py +260 -0
- keras_hub/src/models/whisper/whisper_backbone.py +305 -0
- keras_hub/src/models/whisper/whisper_cached_multi_head_attention.py +153 -0
- keras_hub/src/models/whisper/whisper_decoder.py +141 -0
- keras_hub/src/models/whisper/whisper_encoder.py +106 -0
- keras_hub/src/models/whisper/whisper_preprocessor.py +326 -0
- keras_hub/src/models/whisper/whisper_presets.py +148 -0
- keras_hub/src/models/whisper/whisper_tokenizer.py +163 -0
- keras_hub/src/models/xlm_roberta/__init__.py +26 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_backbone.py +81 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_classifier.py +225 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_masked_lm.py +141 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_masked_lm_preprocessor.py +195 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_preprocessor.py +205 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_presets.py +43 -0
- keras_hub/src/models/xlm_roberta/xlm_roberta_tokenizer.py +191 -0
- keras_hub/src/models/xlnet/__init__.py +13 -0
- keras_hub/src/models/xlnet/relative_attention.py +459 -0
- keras_hub/src/models/xlnet/xlnet_backbone.py +222 -0
- keras_hub/src/models/xlnet/xlnet_content_and_query_embedding.py +133 -0
- keras_hub/src/models/xlnet/xlnet_encoder.py +378 -0
- keras_hub/src/samplers/__init__.py +13 -0
- keras_hub/src/samplers/beam_sampler.py +207 -0
- keras_hub/src/samplers/contrastive_sampler.py +231 -0
- keras_hub/src/samplers/greedy_sampler.py +50 -0
- keras_hub/src/samplers/random_sampler.py +77 -0
- keras_hub/src/samplers/sampler.py +237 -0
- keras_hub/src/samplers/serialization.py +97 -0
- keras_hub/src/samplers/top_k_sampler.py +92 -0
- keras_hub/src/samplers/top_p_sampler.py +113 -0
- keras_hub/src/tests/__init__.py +13 -0
- keras_hub/src/tests/test_case.py +608 -0
- keras_hub/src/tokenizers/__init__.py +13 -0
- keras_hub/src/tokenizers/byte_pair_tokenizer.py +638 -0
- keras_hub/src/tokenizers/byte_tokenizer.py +299 -0
- keras_hub/src/tokenizers/sentence_piece_tokenizer.py +267 -0
- keras_hub/src/tokenizers/sentence_piece_tokenizer_trainer.py +150 -0
- keras_hub/src/tokenizers/tokenizer.py +235 -0
- keras_hub/src/tokenizers/unicode_codepoint_tokenizer.py +355 -0
- keras_hub/src/tokenizers/word_piece_tokenizer.py +544 -0
- keras_hub/src/tokenizers/word_piece_tokenizer_trainer.py +176 -0
- keras_hub/src/utils/__init__.py +13 -0
- keras_hub/src/utils/keras_utils.py +130 -0
- keras_hub/src/utils/pipeline_model.py +293 -0
- keras_hub/src/utils/preset_utils.py +621 -0
- keras_hub/src/utils/python_utils.py +21 -0
- keras_hub/src/utils/tensor_utils.py +206 -0
- keras_hub/src/utils/timm/__init__.py +13 -0
- keras_hub/src/utils/timm/convert.py +37 -0
- keras_hub/src/utils/timm/convert_resnet.py +171 -0
- keras_hub/src/utils/transformers/__init__.py +13 -0
- keras_hub/src/utils/transformers/convert.py +101 -0
- keras_hub/src/utils/transformers/convert_bert.py +173 -0
- keras_hub/src/utils/transformers/convert_distilbert.py +184 -0
- keras_hub/src/utils/transformers/convert_gemma.py +187 -0
- keras_hub/src/utils/transformers/convert_gpt2.py +186 -0
- keras_hub/src/utils/transformers/convert_llama3.py +136 -0
- keras_hub/src/utils/transformers/convert_pali_gemma.py +303 -0
- keras_hub/src/utils/transformers/safetensor_utils.py +97 -0
- keras_hub/src/version_utils.py +23 -0
- keras_hub_nightly-0.15.0.dev20240823171555.dist-info/METADATA +34 -0
- keras_hub_nightly-0.15.0.dev20240823171555.dist-info/RECORD +297 -0
- keras_hub_nightly-0.15.0.dev20240823171555.dist-info/WHEEL +5 -0
- keras_hub_nightly-0.15.0.dev20240823171555.dist-info/top_level.txt +1 -0
@@ -0,0 +1,276 @@
|
|
1
|
+
# Copyright 2024 The KerasHub Authors
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# https://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
|
15
|
+
|
16
|
+
import keras
|
17
|
+
|
18
|
+
from keras_hub.src.api_export import keras_hub_export
|
19
|
+
from keras_hub.src.layers.preprocessing.start_end_packer import StartEndPacker
|
20
|
+
from keras_hub.src.models.bart.bart_tokenizer import BartTokenizer
|
21
|
+
from keras_hub.src.models.preprocessor import Preprocessor
|
22
|
+
from keras_hub.src.utils.keras_utils import (
|
23
|
+
convert_inputs_to_list_of_tensor_segments,
|
24
|
+
)
|
25
|
+
|
26
|
+
|
27
|
+
@keras_hub_export("keras_hub.models.BartPreprocessor")
|
28
|
+
class BartPreprocessor(Preprocessor):
|
29
|
+
"""A BART preprocessing layer which tokenizes and packs inputs.
|
30
|
+
|
31
|
+
This preprocessing layer will do three things:
|
32
|
+
|
33
|
+
1. Tokenize both encoder inputs and decoder inputs using the `tokenizer`.
|
34
|
+
Both inputs can contain only one segment.
|
35
|
+
2. Add the appropriate special tokens - `"<s>"`, `"</s>"` and `"<pad>"`.
|
36
|
+
3. Construct a dictionary with keys `"encoder_token_ids"`,
|
37
|
+
`"encoder_padding_mask"`, `"decoder_token_ids"`, `"decoder_padding_mask"`
|
38
|
+
that can be passed directly to a BART model.
|
39
|
+
|
40
|
+
Args:
|
41
|
+
tokenizer: A `keras_hub.models.BartTokenizer` instance.
|
42
|
+
encoder_sequence_length: The length of the packed encoder inputs.
|
43
|
+
decoder_sequence_length: The length of the packed decoder inputs.
|
44
|
+
|
45
|
+
Call arguments:
|
46
|
+
x: A dictionary with `encoder_text` and `decoder_text` as its keys.
|
47
|
+
Each value in the dictionary should be a tensor of single string
|
48
|
+
sequences. Inputs may be batched or unbatched. Raw python inputs
|
49
|
+
will be converted to tensors.
|
50
|
+
y: Any label data. Will be passed through unaltered.
|
51
|
+
sample_weight: Any label weight data. Will be passed through unaltered.
|
52
|
+
|
53
|
+
Examples:
|
54
|
+
|
55
|
+
Directly calling the layer on data.
|
56
|
+
```python
|
57
|
+
preprocessor = keras_hub.models.BartPreprocessor.from_preset("bart_base_en")
|
58
|
+
|
59
|
+
# Preprocess unbatched inputs.
|
60
|
+
inputs = {
|
61
|
+
"encoder_text": "The fox was sleeping.",
|
62
|
+
"decoder_text": "The fox was awake."
|
63
|
+
}
|
64
|
+
preprocessor(inputs)
|
65
|
+
|
66
|
+
# Preprocess batched inputs.
|
67
|
+
inputs = {
|
68
|
+
"encoder_text": ["The fox was sleeping.", "The lion was quiet."],
|
69
|
+
"decoder_text": ["The fox was awake.", "The lion was roaring."]
|
70
|
+
}
|
71
|
+
preprocessor(inputs)
|
72
|
+
|
73
|
+
# Custom vocabulary.
|
74
|
+
vocab = {
|
75
|
+
"<s>": 0,
|
76
|
+
"<pad>": 1,
|
77
|
+
"</s>": 2,
|
78
|
+
"Ġafter": 5,
|
79
|
+
"noon": 6,
|
80
|
+
"Ġsun": 7,
|
81
|
+
}
|
82
|
+
merges = ["Ġ a", "Ġ s", "Ġ n", "e r", "n o", "o n", "Ġs u", "Ġa f", "no on"]
|
83
|
+
merges += ["Ġsu n", "Ġaf t", "Ġaft er"]
|
84
|
+
|
85
|
+
tokenizer = keras_hub.models.BartTokenizer(
|
86
|
+
vocabulary=vocab,
|
87
|
+
merges=merges,
|
88
|
+
)
|
89
|
+
preprocessor = keras_hub.models.BartPreprocessor(
|
90
|
+
tokenizer=tokenizer,
|
91
|
+
encoder_sequence_length=20,
|
92
|
+
decoder_sequence_length=10,
|
93
|
+
)
|
94
|
+
inputs = {
|
95
|
+
"encoder_text": "The fox was sleeping.",
|
96
|
+
"decoder_text": "The fox was awake."
|
97
|
+
}
|
98
|
+
preprocessor(inputs)
|
99
|
+
```
|
100
|
+
|
101
|
+
Mapping with `tf.data.Dataset`.
|
102
|
+
```python
|
103
|
+
preprocessor = keras_hub.models.BartPreprocessor.from_preset("bart_base_en")
|
104
|
+
|
105
|
+
# Map labeled single sentences.
|
106
|
+
features = {
|
107
|
+
"encoder_text": tf.constant(
|
108
|
+
["The fox was sleeping.", "The lion was quiet."]
|
109
|
+
),
|
110
|
+
"decoder_text": tf.constant(
|
111
|
+
["The fox was awake.", "The lion was silent."]
|
112
|
+
)
|
113
|
+
}
|
114
|
+
labels = tf.constant(["True", "False"])
|
115
|
+
ds = tf.data.Dataset.from_tensor_slices((features, labels))
|
116
|
+
ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
|
117
|
+
|
118
|
+
# Map unlabeled single sentences.
|
119
|
+
features = {
|
120
|
+
"encoder_text": tf.constant(
|
121
|
+
["The fox was sleeping.", "The lion was quiet."]
|
122
|
+
),
|
123
|
+
"decoder_text": tf.constant(
|
124
|
+
["The fox was awake.", "The lion was roaring."]
|
125
|
+
)
|
126
|
+
}
|
127
|
+
ds = tf.data.Dataset.from_tensor_slices(features)
|
128
|
+
ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
|
129
|
+
```
|
130
|
+
"""
|
131
|
+
|
132
|
+
tokenizer_cls = BartTokenizer
|
133
|
+
|
134
|
+
def __init__(
|
135
|
+
self,
|
136
|
+
tokenizer,
|
137
|
+
encoder_sequence_length=1024,
|
138
|
+
decoder_sequence_length=1024,
|
139
|
+
**kwargs,
|
140
|
+
):
|
141
|
+
super().__init__(**kwargs)
|
142
|
+
self.tokenizer = tokenizer
|
143
|
+
self.encoder_packer = None
|
144
|
+
self.decoder_packer = None
|
145
|
+
self.encoder_sequence_length = encoder_sequence_length
|
146
|
+
self.decoder_sequence_length = decoder_sequence_length
|
147
|
+
|
148
|
+
def build(self, input_shape):
|
149
|
+
# Defer packer creation to `build()` so that we can be sure tokenizer
|
150
|
+
# assets have loaded when restoring a saved model.
|
151
|
+
|
152
|
+
# TODO: Use `MultiSegmentPacker` instead of `StartEndPacker` once we
|
153
|
+
# want to move to multi-segment packing and have improved
|
154
|
+
# `MultiSegmentPacker`'s performance.
|
155
|
+
self.encoder_packer = StartEndPacker(
|
156
|
+
start_value=self.tokenizer.start_token_id,
|
157
|
+
end_value=self.tokenizer.end_token_id,
|
158
|
+
pad_value=self.tokenizer.pad_token_id,
|
159
|
+
sequence_length=self.encoder_sequence_length,
|
160
|
+
return_padding_mask=True,
|
161
|
+
)
|
162
|
+
|
163
|
+
# The decoder is packed a bit differently; the format is as follows:
|
164
|
+
# `[end_token_id, start_token_id, tokens..., end_token_id, padding...]`.
|
165
|
+
self.decoder_packer = StartEndPacker(
|
166
|
+
start_value=[
|
167
|
+
self.tokenizer.end_token_id,
|
168
|
+
self.tokenizer.start_token_id,
|
169
|
+
],
|
170
|
+
end_value=self.tokenizer.end_token_id,
|
171
|
+
pad_value=self.tokenizer.pad_token_id,
|
172
|
+
sequence_length=self.decoder_sequence_length,
|
173
|
+
return_padding_mask=True,
|
174
|
+
)
|
175
|
+
self.built = True
|
176
|
+
|
177
|
+
def call(
|
178
|
+
self,
|
179
|
+
x,
|
180
|
+
y=None,
|
181
|
+
sample_weight=None,
|
182
|
+
*,
|
183
|
+
encoder_sequence_length=None,
|
184
|
+
decoder_sequence_length=None,
|
185
|
+
# `sequence_length` is an alias for `decoder_sequence_length`
|
186
|
+
sequence_length=None,
|
187
|
+
):
|
188
|
+
if not (
|
189
|
+
isinstance(x, dict)
|
190
|
+
and all(k in x for k in ("encoder_text", "decoder_text"))
|
191
|
+
):
|
192
|
+
raise ValueError(
|
193
|
+
'`x` must be a dictionary, containing the keys `"encoder_text"`'
|
194
|
+
f' and `"decoder_text"`. Received x={x}.'
|
195
|
+
)
|
196
|
+
|
197
|
+
if encoder_sequence_length is None:
|
198
|
+
encoder_sequence_length = self.encoder_sequence_length
|
199
|
+
decoder_sequence_length = decoder_sequence_length or sequence_length
|
200
|
+
if decoder_sequence_length is None:
|
201
|
+
decoder_sequence_length = self.decoder_sequence_length
|
202
|
+
|
203
|
+
encoder_text = x["encoder_text"]
|
204
|
+
decoder_text = x["decoder_text"]
|
205
|
+
|
206
|
+
encoder_text = convert_inputs_to_list_of_tensor_segments(encoder_text)
|
207
|
+
decoder_text = convert_inputs_to_list_of_tensor_segments(decoder_text)
|
208
|
+
|
209
|
+
if len(encoder_text) > 1 or len(decoder_text) > 1:
|
210
|
+
raise ValueError(
|
211
|
+
'`BARTPreprocessor` requires both `"encoder_text"` and '
|
212
|
+
f'`"decoder_text"` to contain only one segment, but received '
|
213
|
+
f"{len(encoder_text)} and {len(decoder_text)}, respectively."
|
214
|
+
)
|
215
|
+
|
216
|
+
encoder_inputs = self.tokenizer(encoder_text[0])
|
217
|
+
encoder_token_ids, encoder_padding_mask = self.encoder_packer(
|
218
|
+
encoder_inputs,
|
219
|
+
sequence_length=encoder_sequence_length,
|
220
|
+
)
|
221
|
+
|
222
|
+
decoder_inputs = self.tokenizer(decoder_text[0])
|
223
|
+
decoder_token_ids, decoder_padding_mask = self.decoder_packer(
|
224
|
+
decoder_inputs,
|
225
|
+
sequence_length=decoder_sequence_length,
|
226
|
+
)
|
227
|
+
|
228
|
+
x = {
|
229
|
+
"encoder_token_ids": encoder_token_ids,
|
230
|
+
"encoder_padding_mask": encoder_padding_mask,
|
231
|
+
"decoder_token_ids": decoder_token_ids,
|
232
|
+
"decoder_padding_mask": decoder_padding_mask,
|
233
|
+
}
|
234
|
+
|
235
|
+
return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)
|
236
|
+
|
237
|
+
def get_config(self):
|
238
|
+
config = super().get_config()
|
239
|
+
config.update(
|
240
|
+
{
|
241
|
+
"encoder_sequence_length": self.encoder_sequence_length,
|
242
|
+
"decoder_sequence_length": self.decoder_sequence_length,
|
243
|
+
}
|
244
|
+
)
|
245
|
+
return config
|
246
|
+
|
247
|
+
@property
|
248
|
+
def encoder_sequence_length(self):
|
249
|
+
"""The padded length of encoder input sequences."""
|
250
|
+
return self._encoder_sequence_length
|
251
|
+
|
252
|
+
@encoder_sequence_length.setter
|
253
|
+
def encoder_sequence_length(self, value):
|
254
|
+
self._encoder_sequence_length = value
|
255
|
+
if self.encoder_packer is not None:
|
256
|
+
self.encoder_packer.sequence_length = value
|
257
|
+
|
258
|
+
@property
|
259
|
+
def decoder_sequence_length(self):
|
260
|
+
"""The padded length of decoder input sequences."""
|
261
|
+
return self._decoder_sequence_length
|
262
|
+
|
263
|
+
@decoder_sequence_length.setter
|
264
|
+
def decoder_sequence_length(self, value):
|
265
|
+
self._decoder_sequence_length = value
|
266
|
+
if self.decoder_packer is not None:
|
267
|
+
self.decoder_packer.sequence_length = value
|
268
|
+
|
269
|
+
@property
|
270
|
+
def sequence_length(self):
|
271
|
+
"""Alias for `decoder_sequence_length`."""
|
272
|
+
return self.decoder_sequence_length
|
273
|
+
|
274
|
+
@sequence_length.setter
|
275
|
+
def sequence_length(self, value):
|
276
|
+
self.decoder_sequence_length = value
|
@@ -0,0 +1,74 @@
|
|
1
|
+
# Copyright 2024 The KerasHub Authors
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# https://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
"""BART model preset configurations."""
|
15
|
+
|
16
|
+
backbone_presets = {
|
17
|
+
"bart_base_en": {
|
18
|
+
"metadata": {
|
19
|
+
"description": (
|
20
|
+
"6-layer BART model where case is maintained. "
|
21
|
+
"Trained on BookCorpus, English Wikipedia and CommonCrawl."
|
22
|
+
),
|
23
|
+
"params": 139417344,
|
24
|
+
"official_name": "BART",
|
25
|
+
"path": "bart",
|
26
|
+
"model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/bart/README.md",
|
27
|
+
},
|
28
|
+
"kaggle_handle": "kaggle://keras/bart/keras/bart_base_en/2",
|
29
|
+
},
|
30
|
+
"bart_large_en": {
|
31
|
+
"metadata": {
|
32
|
+
"description": (
|
33
|
+
"12-layer BART model where case is maintained. "
|
34
|
+
"Trained on BookCorpus, English Wikipedia and CommonCrawl."
|
35
|
+
),
|
36
|
+
"params": 406287360,
|
37
|
+
"official_name": "BART",
|
38
|
+
"path": "bart",
|
39
|
+
"model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/bart/README.md",
|
40
|
+
},
|
41
|
+
"config": {
|
42
|
+
"vocabulary_size": 50265,
|
43
|
+
"num_layers": 12,
|
44
|
+
"num_heads": 16,
|
45
|
+
"hidden_dim": 1024,
|
46
|
+
"intermediate_dim": 4096,
|
47
|
+
"dropout": 0.1,
|
48
|
+
"max_sequence_length": 1024,
|
49
|
+
},
|
50
|
+
"kaggle_handle": "kaggle://keras/bart/keras/bart_large_en/2",
|
51
|
+
},
|
52
|
+
"bart_large_en_cnn": {
|
53
|
+
"metadata": {
|
54
|
+
"description": (
|
55
|
+
"The `bart_large_en` backbone model fine-tuned on the CNN+DM "
|
56
|
+
"summarization dataset."
|
57
|
+
),
|
58
|
+
"params": 406287360,
|
59
|
+
"official_name": "BART",
|
60
|
+
"path": "bart",
|
61
|
+
"model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/bart/README.md",
|
62
|
+
},
|
63
|
+
"config": {
|
64
|
+
"vocabulary_size": 50264,
|
65
|
+
"num_layers": 12,
|
66
|
+
"num_heads": 16,
|
67
|
+
"hidden_dim": 1024,
|
68
|
+
"intermediate_dim": 4096,
|
69
|
+
"dropout": 0.1,
|
70
|
+
"max_sequence_length": 1024,
|
71
|
+
},
|
72
|
+
"kaggle_handle": "kaggle://keras/bart/keras/bart_large_en_cnn/2",
|
73
|
+
},
|
74
|
+
}
|