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 +1,95 @@
|
|
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
|
+
"""XLM-RoBERTa model preset configurations."""
|
15
|
+
|
16
|
+
backbone_presets = {
|
17
|
+
"t5_small_multi": {
|
18
|
+
"metadata": {
|
19
|
+
"description": (
|
20
|
+
"8-layer T5 model. Trained on the Colossal Clean Crawled "
|
21
|
+
"Corpus (C4)."
|
22
|
+
),
|
23
|
+
"params": 0,
|
24
|
+
"official_name": "T5",
|
25
|
+
"path": "t5",
|
26
|
+
"model_card": "https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md",
|
27
|
+
},
|
28
|
+
"kaggle_handle": "kaggle://keras/t5/keras/t5_small_multi/2",
|
29
|
+
},
|
30
|
+
"t5_base_multi": {
|
31
|
+
"metadata": {
|
32
|
+
"description": (
|
33
|
+
"12-layer T5 model. Trained on the Colossal Clean Crawled "
|
34
|
+
"Corpus (C4)."
|
35
|
+
),
|
36
|
+
"params": 0,
|
37
|
+
"official_name": "T5",
|
38
|
+
"path": "t5",
|
39
|
+
"model_card": "https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md",
|
40
|
+
},
|
41
|
+
"kaggle_handle": "kaggle://keras/t5/keras/t5_base_multi/2",
|
42
|
+
},
|
43
|
+
"t5_large_multi": {
|
44
|
+
"metadata": {
|
45
|
+
"description": (
|
46
|
+
"24-layer T5 model. Trained on the Colossal Clean Crawled "
|
47
|
+
"Corpus (C4)."
|
48
|
+
),
|
49
|
+
"params": 0,
|
50
|
+
"official_name": "T5",
|
51
|
+
"path": "t5",
|
52
|
+
"model_card": "https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md",
|
53
|
+
},
|
54
|
+
"kaggle_handle": "kaggle://keras/t5/keras/t5_large_multi/2",
|
55
|
+
},
|
56
|
+
"flan_small_multi": {
|
57
|
+
"metadata": {
|
58
|
+
"description": (
|
59
|
+
"8-layer T5 model. Trained on the Colossal Clean Crawled "
|
60
|
+
"Corpus (C4)."
|
61
|
+
),
|
62
|
+
"params": 0,
|
63
|
+
"official_name": "T5",
|
64
|
+
"path": "t5",
|
65
|
+
"model_card": "https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md",
|
66
|
+
},
|
67
|
+
"kaggle_handle": "kaggle://keras/t5/keras/flan_small_multi/2",
|
68
|
+
},
|
69
|
+
"flan_base_multi": {
|
70
|
+
"metadata": {
|
71
|
+
"description": (
|
72
|
+
"12-layer T5 model. Trained on the Colossal Clean Crawled "
|
73
|
+
"Corpus (C4)."
|
74
|
+
),
|
75
|
+
"params": 0,
|
76
|
+
"official_name": "T5",
|
77
|
+
"path": "t5",
|
78
|
+
"model_card": "https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md",
|
79
|
+
},
|
80
|
+
"kaggle_handle": "kaggle://keras/t5/keras/flan_base_multi/2",
|
81
|
+
},
|
82
|
+
"flan_large_multi": {
|
83
|
+
"metadata": {
|
84
|
+
"description": (
|
85
|
+
"24-layer T5 model. Trained on the Colossal Clean Crawled "
|
86
|
+
"Corpus (C4)."
|
87
|
+
),
|
88
|
+
"params": 0,
|
89
|
+
"official_name": "T5",
|
90
|
+
"path": "t5",
|
91
|
+
"model_card": "https://github.com/google-research/text-to-text-transfer-transformer/blob/main/README.md",
|
92
|
+
},
|
93
|
+
"kaggle_handle": "kaggle://keras/t5/keras/flan_large_multi/2",
|
94
|
+
},
|
95
|
+
}
|
@@ -0,0 +1,100 @@
|
|
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
|
+
from keras_hub.src.api_export import keras_hub_export
|
16
|
+
from keras_hub.src.tokenizers.sentence_piece_tokenizer import (
|
17
|
+
SentencePieceTokenizer,
|
18
|
+
)
|
19
|
+
|
20
|
+
|
21
|
+
@keras_hub_export("keras_hub.models.T5Tokenizer")
|
22
|
+
class T5Tokenizer(SentencePieceTokenizer):
|
23
|
+
"""T5 tokenizer layer based on SentencePiece.
|
24
|
+
|
25
|
+
This tokenizer class will tokenize raw strings into integer sequences and
|
26
|
+
is based on `keras_hub.tokenizers.SentencePieceTokenizer`. Unlike the
|
27
|
+
underlying tokenizer, it will check for all special tokens needed by
|
28
|
+
T5 models and provides a `from_preset()` method to automatically
|
29
|
+
download a matching vocabulary for a T5 preset.
|
30
|
+
|
31
|
+
If input is a batch of strings (rank > 0), the layer will output a
|
32
|
+
`tf.RaggedTensor` where the last dimension of the output is ragged.
|
33
|
+
|
34
|
+
If input is a scalar string (rank == 0), the layer will output a dense
|
35
|
+
`tf.Tensor` with static shape `[None]`.
|
36
|
+
|
37
|
+
Args:
|
38
|
+
proto: Either a `string` path to a SentencePiece proto file, or a
|
39
|
+
`bytes` object with a serialized SentencePiece proto. See the
|
40
|
+
[SentencePiece repository](https://github.com/google/sentencepiece)
|
41
|
+
for more details on the format.
|
42
|
+
|
43
|
+
Examples:
|
44
|
+
|
45
|
+
```python
|
46
|
+
bytes_io = io.BytesIO()
|
47
|
+
ds = tf.data.Dataset.from_tensor_slices(["The quick brown fox jumped."])
|
48
|
+
sentencepiece.SentencePieceTrainer.train(
|
49
|
+
sentence_iterator=ds.as_numpy_iterator(),
|
50
|
+
model_writer=bytes_io,
|
51
|
+
vocab_size=8,
|
52
|
+
model_type="WORD",
|
53
|
+
bos_id=-1,
|
54
|
+
pad_id=0,
|
55
|
+
eos_id=1,
|
56
|
+
unk_id=2,
|
57
|
+
pad_piece="<pad>",
|
58
|
+
eos_piece="</s>",
|
59
|
+
unk_piece="<unk>",
|
60
|
+
)
|
61
|
+
tokenizer = keras_hub.models.T5Tokenizer(
|
62
|
+
proto=bytes_io.getvalue(),
|
63
|
+
)
|
64
|
+
tokenizer("The quick brown fox jumped.")
|
65
|
+
|
66
|
+
# Batched inputs.
|
67
|
+
tokenizer(["the quick brown fox", "the earth is round"])
|
68
|
+
|
69
|
+
# Unbatched inputs.
|
70
|
+
tokenizer("the quick brown fox")
|
71
|
+
|
72
|
+
# Detokenization.
|
73
|
+
tokenizer.detokenize(tokenizer("The quick brown fox jumped."))
|
74
|
+
```
|
75
|
+
"""
|
76
|
+
|
77
|
+
def __init__(self, proto, **kwargs):
|
78
|
+
self.end_token = "</s>"
|
79
|
+
self.pad_token = "<pad>"
|
80
|
+
|
81
|
+
super().__init__(proto=proto, **kwargs)
|
82
|
+
|
83
|
+
def set_proto(self, proto):
|
84
|
+
super().set_proto(proto)
|
85
|
+
if proto is not None:
|
86
|
+
for token in [self.end_token, self.pad_token]:
|
87
|
+
if token not in self.get_vocabulary():
|
88
|
+
raise ValueError(
|
89
|
+
f"Cannot find token `'{token}'` in the provided "
|
90
|
+
f"`vocabulary`. Please provide `'{token}'` in your "
|
91
|
+
"`vocabulary` or use a pretrained `vocabulary` name."
|
92
|
+
)
|
93
|
+
self.end_token_id = self.token_to_id(self.end_token)
|
94
|
+
self.pad_token_id = self.token_to_id(self.pad_token)
|
95
|
+
# T5 uses the same start token as end token, i.e., "<\s>".
|
96
|
+
self.start_token_id = self.end_token_id
|
97
|
+
else:
|
98
|
+
self.end_token_id = None
|
99
|
+
self.pad_token_id = None
|
100
|
+
self.start_token_id = None
|
@@ -0,0 +1,178 @@
|
|
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
|
+
import keras
|
16
|
+
from keras import ops
|
17
|
+
|
18
|
+
from keras_hub.src.layers.modeling.transformer_layer_utils import (
|
19
|
+
compute_causal_mask,
|
20
|
+
)
|
21
|
+
from keras_hub.src.models.t5.t5_layer_norm import T5LayerNorm
|
22
|
+
from keras_hub.src.models.t5.t5_multi_head_attention import T5MultiHeadAttention
|
23
|
+
|
24
|
+
|
25
|
+
class T5TransformerLayer(keras.layers.Layer):
|
26
|
+
def __init__(
|
27
|
+
self,
|
28
|
+
is_decoder,
|
29
|
+
hidden_dim,
|
30
|
+
intermediate_dim,
|
31
|
+
key_value_dim,
|
32
|
+
dropout,
|
33
|
+
activation,
|
34
|
+
layer_norm_epsilon,
|
35
|
+
num_heads,
|
36
|
+
use_gated_activation=False,
|
37
|
+
use_relative_attention_bias=False,
|
38
|
+
**kwargs,
|
39
|
+
):
|
40
|
+
super().__init__(**kwargs)
|
41
|
+
self.is_decoder = is_decoder
|
42
|
+
self.use_gated_activation = use_gated_activation
|
43
|
+
|
44
|
+
self.self_attention = T5MultiHeadAttention(
|
45
|
+
is_decoder=is_decoder,
|
46
|
+
hidden_dim=hidden_dim,
|
47
|
+
key_value_dim=key_value_dim,
|
48
|
+
num_heads=num_heads,
|
49
|
+
dropout=dropout,
|
50
|
+
use_relative_attention_bias=use_relative_attention_bias,
|
51
|
+
dtype=self.dtype_policy,
|
52
|
+
name="self_attention",
|
53
|
+
)
|
54
|
+
self.self_attention_layer_norm = T5LayerNorm(
|
55
|
+
layer_norm_epsilon,
|
56
|
+
dtype=self.dtype_policy,
|
57
|
+
)
|
58
|
+
self.self_attention_dropout = keras.layers.Dropout(
|
59
|
+
dropout,
|
60
|
+
dtype=self.dtype_policy,
|
61
|
+
)
|
62
|
+
|
63
|
+
if self.is_decoder:
|
64
|
+
self.cross_attention = T5MultiHeadAttention(
|
65
|
+
is_decoder=is_decoder,
|
66
|
+
hidden_dim=hidden_dim,
|
67
|
+
key_value_dim=key_value_dim,
|
68
|
+
num_heads=num_heads,
|
69
|
+
dropout=dropout,
|
70
|
+
use_relative_attention_bias=False,
|
71
|
+
dtype=self.dtype_policy,
|
72
|
+
name="cross_attention",
|
73
|
+
)
|
74
|
+
self.cross_attention_layer_norm = T5LayerNorm(
|
75
|
+
layer_norm_epsilon,
|
76
|
+
dtype=self.dtype_policy,
|
77
|
+
)
|
78
|
+
self.cross_attention_dropout = keras.layers.Dropout(
|
79
|
+
dropout,
|
80
|
+
dtype=self.dtype_policy,
|
81
|
+
)
|
82
|
+
|
83
|
+
self.input_projector = keras.layers.Dense(
|
84
|
+
intermediate_dim,
|
85
|
+
use_bias=False,
|
86
|
+
activation=keras.activations.get(activation),
|
87
|
+
kernel_initializer=keras.initializers.RandomNormal(
|
88
|
+
mean=0, stddev=hidden_dim**-0.5
|
89
|
+
),
|
90
|
+
dtype=self.dtype_policy,
|
91
|
+
name="input_projector",
|
92
|
+
)
|
93
|
+
if self.use_gated_activation:
|
94
|
+
self.gate_projector = keras.layers.Dense(
|
95
|
+
intermediate_dim,
|
96
|
+
use_bias=False,
|
97
|
+
kernel_initializer=keras.initializers.RandomNormal(
|
98
|
+
mean=0, stddev=hidden_dim**-0.5
|
99
|
+
),
|
100
|
+
dtype=self.dtype_policy,
|
101
|
+
name="gate_projector",
|
102
|
+
)
|
103
|
+
self.output_projector = keras.layers.Dense(
|
104
|
+
hidden_dim,
|
105
|
+
use_bias=False,
|
106
|
+
kernel_initializer=keras.initializers.RandomNormal(
|
107
|
+
mean=0, stddev=intermediate_dim**-0.5
|
108
|
+
),
|
109
|
+
dtype=self.dtype_policy,
|
110
|
+
name="output_projector",
|
111
|
+
)
|
112
|
+
self.layer_norm = T5LayerNorm(
|
113
|
+
epsilon=layer_norm_epsilon,
|
114
|
+
dtype=self.dtype_policy,
|
115
|
+
)
|
116
|
+
self.dropout_layer = keras.layers.Dropout(
|
117
|
+
dropout,
|
118
|
+
dtype=self.dtype_policy,
|
119
|
+
)
|
120
|
+
|
121
|
+
def call(
|
122
|
+
self,
|
123
|
+
hidden_states,
|
124
|
+
attention_mask=None,
|
125
|
+
position_bias=None,
|
126
|
+
encoder_hidden_states=None,
|
127
|
+
encoder_attention_mask=None,
|
128
|
+
use_causal_mask=False,
|
129
|
+
training=False,
|
130
|
+
):
|
131
|
+
if use_causal_mask:
|
132
|
+
shape = ops.shape(hidden_states)
|
133
|
+
batch_size, length = shape[0], shape[1]
|
134
|
+
causal_mask = compute_causal_mask(batch_size, length, length)
|
135
|
+
attention_mask = causal_mask & ops.cast(attention_mask, "bool")
|
136
|
+
|
137
|
+
x = hidden_states # Intermediate result.
|
138
|
+
|
139
|
+
residual = x
|
140
|
+
x = self.self_attention_layer_norm(x)
|
141
|
+
x, position_bias = self.self_attention(
|
142
|
+
x,
|
143
|
+
mask=attention_mask,
|
144
|
+
position_bias=position_bias,
|
145
|
+
training=training,
|
146
|
+
)
|
147
|
+
x = self.self_attention_dropout(x, training=training)
|
148
|
+
x = x + residual
|
149
|
+
|
150
|
+
if self.is_decoder:
|
151
|
+
residual = x
|
152
|
+
x = self.cross_attention_layer_norm(x)
|
153
|
+
x, _ = self.cross_attention(
|
154
|
+
x,
|
155
|
+
key_value_states=encoder_hidden_states,
|
156
|
+
mask=encoder_attention_mask,
|
157
|
+
training=training,
|
158
|
+
)
|
159
|
+
x = self.cross_attention_dropout(x, training=training)
|
160
|
+
x = x + residual
|
161
|
+
|
162
|
+
residual = x
|
163
|
+
x = self.layer_norm(x)
|
164
|
+
if self.use_gated_activation:
|
165
|
+
hidden_activation = self.input_projector(x)
|
166
|
+
hidden_linear = self.gate_projector(x)
|
167
|
+
x = hidden_activation * hidden_linear
|
168
|
+
else:
|
169
|
+
x = self.input_projector(x)
|
170
|
+
x = self.dropout_layer(x, training=training)
|
171
|
+
x = self.output_projector(x)
|
172
|
+
x = self.dropout_layer(x, training=training)
|
173
|
+
x = x + residual
|
174
|
+
|
175
|
+
if position_bias is not None:
|
176
|
+
return x, position_bias
|
177
|
+
else:
|
178
|
+
return x
|