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 +1,43 @@
|
|
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
|
+
"""FNet model preset configurations."""
|
15
|
+
|
16
|
+
backbone_presets = {
|
17
|
+
"f_net_base_en": {
|
18
|
+
"metadata": {
|
19
|
+
"description": (
|
20
|
+
"12-layer FNet model where case is maintained. "
|
21
|
+
"Trained on the C4 dataset."
|
22
|
+
),
|
23
|
+
"params": 82861056,
|
24
|
+
"official_name": "FNet",
|
25
|
+
"path": "f_net",
|
26
|
+
"model_card": "https://github.com/google-research/google-research/blob/master/f_net/README.md",
|
27
|
+
},
|
28
|
+
"kaggle_handle": "kaggle://keras/f_net/keras/f_net_base_en/2",
|
29
|
+
},
|
30
|
+
"f_net_large_en": {
|
31
|
+
"metadata": {
|
32
|
+
"description": (
|
33
|
+
"24-layer FNet model where case is maintained. "
|
34
|
+
"Trained on the C4 dataset."
|
35
|
+
),
|
36
|
+
"params": 236945408,
|
37
|
+
"official_name": "FNet",
|
38
|
+
"path": "f_net",
|
39
|
+
"model_card": "https://github.com/google-research/google-research/blob/master/f_net/README.md",
|
40
|
+
},
|
41
|
+
"kaggle_handle": "kaggle://keras/f_net/keras/f_net_large_en/2",
|
42
|
+
},
|
43
|
+
}
|
@@ -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
|
+
|
15
|
+
|
16
|
+
from keras_hub.src.api_export import keras_hub_export
|
17
|
+
from keras_hub.src.tokenizers.sentence_piece_tokenizer import (
|
18
|
+
SentencePieceTokenizer,
|
19
|
+
)
|
20
|
+
|
21
|
+
|
22
|
+
@keras_hub_export("keras_hub.models.FNetTokenizer")
|
23
|
+
class FNetTokenizer(SentencePieceTokenizer):
|
24
|
+
"""FNet tokenizer layer based on SentencePiece.
|
25
|
+
|
26
|
+
This tokenizer class will tokenize raw strings into integer sequences and
|
27
|
+
is based on `keras_hub.tokenizers.SentencePieceTokenizer`. Unlike the
|
28
|
+
underlying tokenizer, it will check for all special tokens needed by
|
29
|
+
FNet models and provides a `from_preset()` method to automatically
|
30
|
+
download a matching vocabulary for a FNet preset.
|
31
|
+
|
32
|
+
This tokenizer does not provide truncation or padding of inputs. It can be
|
33
|
+
combined with a `keras_hub.models.FNetPreprocessor` layer for input
|
34
|
+
packing.
|
35
|
+
|
36
|
+
If input is a batch of strings (rank > 0), the layer will output a
|
37
|
+
`tf.RaggedTensor` where the last dimension of the output is ragged.
|
38
|
+
|
39
|
+
If input is a scalar string (rank == 0), the layer will output a dense
|
40
|
+
`tf.Tensor` with static shape `[None]`.
|
41
|
+
|
42
|
+
Args:
|
43
|
+
proto: Either a `string` path to a SentencePiece proto file, or a
|
44
|
+
`bytes` object with a serialized SentencePiece proto. See the
|
45
|
+
[SentencePiece repository](https://github.com/google/sentencepiece)
|
46
|
+
for more details on the format.
|
47
|
+
|
48
|
+
Examples:
|
49
|
+
```python
|
50
|
+
# Unbatched input.
|
51
|
+
tokenizer = keras_hub.models.FNetTokenizer.from_preset(
|
52
|
+
"f_net_base_en",
|
53
|
+
)
|
54
|
+
tokenizer("The quick brown fox jumped.")
|
55
|
+
|
56
|
+
# Batched input.
|
57
|
+
tokenizer(["The quick brown fox jumped.", "The fox slept."])
|
58
|
+
|
59
|
+
# Detokenization.
|
60
|
+
tokenizer.detokenize(tokenizer("The quick brown fox jumped."))
|
61
|
+
```
|
62
|
+
"""
|
63
|
+
|
64
|
+
def __init__(self, proto, **kwargs):
|
65
|
+
self.cls_token = "[CLS]"
|
66
|
+
self.sep_token = "[SEP]"
|
67
|
+
self.pad_token = "<pad>"
|
68
|
+
self.mask_token = "[MASK]"
|
69
|
+
super().__init__(proto=proto, **kwargs)
|
70
|
+
|
71
|
+
def set_proto(self, proto):
|
72
|
+
super().set_proto(proto)
|
73
|
+
if proto is not None:
|
74
|
+
for token in [
|
75
|
+
self.cls_token,
|
76
|
+
self.sep_token,
|
77
|
+
self.pad_token,
|
78
|
+
self.mask_token,
|
79
|
+
]:
|
80
|
+
if token not in self.get_vocabulary():
|
81
|
+
raise ValueError(
|
82
|
+
f"Cannot find token `'{token}'` in the provided "
|
83
|
+
f"`vocabulary`. Please provide `'{token}'` in your "
|
84
|
+
"`vocabulary` or use a pretrained `vocabulary` name."
|
85
|
+
)
|
86
|
+
|
87
|
+
self.cls_token_id = self.token_to_id(self.cls_token)
|
88
|
+
self.sep_token_id = self.token_to_id(self.sep_token)
|
89
|
+
self.pad_token_id = self.token_to_id(self.pad_token)
|
90
|
+
self.mask_token_id = self.token_to_id(self.mask_token)
|
91
|
+
else:
|
92
|
+
self.cls_token_id = None
|
93
|
+
self.sep_token_id = None
|
94
|
+
self.pad_token_id = None
|
95
|
+
self.mask_token_id = None
|
@@ -0,0 +1,20 @@
|
|
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.models.falcon.falcon_backbone import FalconBackbone
|
16
|
+
from keras_hub.src.models.falcon.falcon_presets import backbone_presets
|
17
|
+
from keras_hub.src.models.falcon.falcon_tokenizer import FalconTokenizer
|
18
|
+
from keras_hub.src.utils.preset_utils import register_presets
|
19
|
+
|
20
|
+
register_presets(backbone_presets, (FalconBackbone, FalconTokenizer))
|
@@ -0,0 +1,156 @@
|
|
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
|
+
import math
|
15
|
+
|
16
|
+
import keras
|
17
|
+
from keras import ops
|
18
|
+
|
19
|
+
|
20
|
+
class FalconAttention(keras.layers.Layer):
|
21
|
+
def __init__(
|
22
|
+
self,
|
23
|
+
num_heads,
|
24
|
+
attention_dropout_rate,
|
25
|
+
**kwargs,
|
26
|
+
):
|
27
|
+
super().__init__(**kwargs)
|
28
|
+
self.num_heads = num_heads
|
29
|
+
self.attention_dropout_rate = attention_dropout_rate
|
30
|
+
|
31
|
+
def build(self, inputs_shape):
|
32
|
+
# Einsum variables:
|
33
|
+
# b = batch size
|
34
|
+
# q = query length
|
35
|
+
# m = model dim
|
36
|
+
# n = num attention heads
|
37
|
+
# h = head dim
|
38
|
+
# k = key/value length
|
39
|
+
|
40
|
+
batch_size, seq_length, hidden_dim = inputs_shape
|
41
|
+
|
42
|
+
self.head_dim = hidden_dim // self.num_heads
|
43
|
+
|
44
|
+
# Layer-wise attention scaling
|
45
|
+
self.inv_norm_factor = 1.0 / math.sqrt(self.head_dim)
|
46
|
+
|
47
|
+
self.query_dense = keras.layers.EinsumDense(
|
48
|
+
equation="bqm,mnh->bqnh",
|
49
|
+
output_shape=(None, self.num_heads, self.head_dim),
|
50
|
+
bias_axes="nh",
|
51
|
+
dtype=self.dtype_policy,
|
52
|
+
name="query_dense",
|
53
|
+
)
|
54
|
+
self.query_dense.build(inputs_shape)
|
55
|
+
|
56
|
+
self.key_dense = keras.layers.EinsumDense(
|
57
|
+
equation="bkm,mnh->bknh",
|
58
|
+
output_shape=(None, self.num_heads, self.head_dim),
|
59
|
+
bias_axes="nh",
|
60
|
+
dtype=self.dtype_policy,
|
61
|
+
name="key_dense",
|
62
|
+
)
|
63
|
+
self.key_dense.build(inputs_shape)
|
64
|
+
|
65
|
+
self.value_dense = keras.layers.EinsumDense(
|
66
|
+
equation="bkm,mnh->bknh",
|
67
|
+
output_shape=(None, self.num_heads, self.head_dim),
|
68
|
+
bias_axes="nh",
|
69
|
+
dtype=self.dtype_policy,
|
70
|
+
name="value_dense",
|
71
|
+
)
|
72
|
+
self.value_dense.build(inputs_shape)
|
73
|
+
|
74
|
+
self.attention_dropout = keras.layers.Dropout(
|
75
|
+
rate=self.attention_dropout_rate,
|
76
|
+
dtype=self.dtype_policy,
|
77
|
+
name="attention_dropout",
|
78
|
+
)
|
79
|
+
|
80
|
+
self.output_dense = keras.layers.Dense(
|
81
|
+
hidden_dim,
|
82
|
+
dtype=self.dtype_policy,
|
83
|
+
name="output_dense",
|
84
|
+
)
|
85
|
+
self.output_dense.build(inputs_shape)
|
86
|
+
|
87
|
+
self.softmax = keras.layers.Softmax(dtype="float32", name="softmax")
|
88
|
+
|
89
|
+
self.built = True
|
90
|
+
|
91
|
+
def call(
|
92
|
+
self,
|
93
|
+
inputs,
|
94
|
+
alibi,
|
95
|
+
attention_mask=None,
|
96
|
+
cache=None,
|
97
|
+
cache_update_index=None,
|
98
|
+
):
|
99
|
+
batch_size, seq_length, hidden_dim = ops.shape(inputs)
|
100
|
+
|
101
|
+
query = self.query_dense(inputs)
|
102
|
+
key = self.key_dense(inputs)
|
103
|
+
value = self.value_dense(inputs)
|
104
|
+
|
105
|
+
if cache is not None:
|
106
|
+
key_cache = cache[:, 0, ...]
|
107
|
+
value_cache = cache[:, 1, ...]
|
108
|
+
if cache_update_index is None:
|
109
|
+
key = key_cache
|
110
|
+
value = value_cache
|
111
|
+
else:
|
112
|
+
start = [0, cache_update_index, 0, 0]
|
113
|
+
key = ops.slice_update(key_cache, start, key)
|
114
|
+
value = ops.slice_update(value_cache, start, value)
|
115
|
+
cache = ops.stack((key, value), axis=1)
|
116
|
+
else:
|
117
|
+
if cache_update_index is not None:
|
118
|
+
raise ValueError(
|
119
|
+
"`cache_update_index` should not be set if `cache` is "
|
120
|
+
f"`None`. Received: cache={cache}, "
|
121
|
+
f"cache_update_index={cache_update_index}"
|
122
|
+
)
|
123
|
+
|
124
|
+
attention_scores = ops.einsum("bqnh,bknh->bnqk", query, key)
|
125
|
+
attention_scores = ops.add(attention_scores, alibi)
|
126
|
+
attention_scores = (
|
127
|
+
attention_scores * self.inv_norm_factor
|
128
|
+
) # [batch_size, num_heads, query_length, kv_length]
|
129
|
+
attention_scores = self.softmax(
|
130
|
+
attention_scores, ops.expand_dims(attention_mask, 1)
|
131
|
+
)
|
132
|
+
attention_scores = self.attention_dropout(attention_scores)
|
133
|
+
attention_output = ops.einsum(
|
134
|
+
"bnqk,bknh->bqnh", attention_scores, value
|
135
|
+
)
|
136
|
+
attention_output = ops.reshape(
|
137
|
+
attention_output,
|
138
|
+
[batch_size, seq_length, self.num_heads * self.head_dim],
|
139
|
+
) # [batch_size, query_length, hidden_dim]
|
140
|
+
|
141
|
+
attention_output = self.output_dense(attention_output)
|
142
|
+
|
143
|
+
if cache is not None:
|
144
|
+
return attention_output, cache
|
145
|
+
|
146
|
+
return attention_output
|
147
|
+
|
148
|
+
def get_config(self):
|
149
|
+
config = super().get_config()
|
150
|
+
config.update(
|
151
|
+
{
|
152
|
+
"num_heads": self.num_heads,
|
153
|
+
"attention_dropout_rate": self.attention_dropout_rate,
|
154
|
+
}
|
155
|
+
)
|
156
|
+
return config
|
@@ -0,0 +1,164 @@
|
|
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
|
+
import keras
|
15
|
+
|
16
|
+
from keras_hub.src.api_export import keras_hub_export
|
17
|
+
from keras_hub.src.layers.modeling.reversible_embedding import (
|
18
|
+
ReversibleEmbedding,
|
19
|
+
)
|
20
|
+
from keras_hub.src.models.backbone import Backbone
|
21
|
+
from keras_hub.src.models.falcon.falcon_transformer_decoder import (
|
22
|
+
FalconTransformerDecoder,
|
23
|
+
)
|
24
|
+
|
25
|
+
|
26
|
+
@keras_hub_export("keras_hub.models.FalconBackbone")
|
27
|
+
class FalconBackbone(Backbone):
|
28
|
+
"""The Falcon core architecure.
|
29
|
+
|
30
|
+
This network implements a Transformer-based decoder-only network,
|
31
|
+
[Falcon](https://arxiv.org/abs/2306.01116).
|
32
|
+
|
33
|
+
Args:
|
34
|
+
vocabulary_size: int. The size of the token vocabulary.
|
35
|
+
num_layers: int. The number of transformer layers.
|
36
|
+
num_attention_heads: int. The number of attention heads for each transformer.
|
37
|
+
The hidden size must be divisible by the number of attention heads.
|
38
|
+
hidden_dim: int. The dimensionality of the embeddings and hidden states.
|
39
|
+
intermediate_dim: int. The output dimension of the first Dense layer in
|
40
|
+
the MLP network of each transformer.
|
41
|
+
layer_norm_epsilon: float. Epsilon for the layer normalization layers in
|
42
|
+
the transformer decoder.
|
43
|
+
attention_dropout_rate: float. Dropout probability for the attention.
|
44
|
+
feedforward_dropout_rate: flaot. Dropout probability for the feedforward.
|
45
|
+
dtype: string or `keras.mixed_precision.DTypePolicy`. The dtype to use
|
46
|
+
for model computations and weights. Note that some computations,
|
47
|
+
such as softmax and layer normalization, will always be done at
|
48
|
+
float32 precision regardless of dtype.
|
49
|
+
|
50
|
+
Examples:
|
51
|
+
```python
|
52
|
+
input_data = {
|
53
|
+
"token_ids": np.ones(shape=(1, 12), dtype="int32"),
|
54
|
+
"padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]]),
|
55
|
+
}
|
56
|
+
|
57
|
+
# Pretrained Falcon decoder.
|
58
|
+
# TODO: Update the preset.
|
59
|
+
model = keras_hub.models.FalconBackbone.from_preset("falcon_preset")
|
60
|
+
model(input_data)
|
61
|
+
|
62
|
+
# Randomly initialized Falcon decoder with a custom config.
|
63
|
+
model = keras_hub.models.FalconBackbone(
|
64
|
+
vocabulary_size=10,
|
65
|
+
num_layers=2,
|
66
|
+
num_attention_heads=2,
|
67
|
+
hidden_dim=32,
|
68
|
+
intermediate_dim=32*4,
|
69
|
+
layer_norm_epsilon=1e-5,
|
70
|
+
attention_dropout_rate=0,
|
71
|
+
feedforward_dropout_rate=0,
|
72
|
+
dtype="float32",
|
73
|
+
)
|
74
|
+
model(input_data)
|
75
|
+
```
|
76
|
+
"""
|
77
|
+
|
78
|
+
def __init__(
|
79
|
+
self,
|
80
|
+
vocabulary_size,
|
81
|
+
num_layers,
|
82
|
+
num_attention_heads,
|
83
|
+
hidden_dim,
|
84
|
+
intermediate_dim,
|
85
|
+
layer_norm_epsilon=1e-5,
|
86
|
+
attention_dropout_rate=0,
|
87
|
+
feedforward_dropout_rate=0,
|
88
|
+
dtype=None,
|
89
|
+
**kwargs,
|
90
|
+
):
|
91
|
+
# === Layers ===
|
92
|
+
self.token_embedding = ReversibleEmbedding(
|
93
|
+
input_dim=vocabulary_size,
|
94
|
+
output_dim=hidden_dim,
|
95
|
+
dtype=dtype,
|
96
|
+
name="token_embedding",
|
97
|
+
)
|
98
|
+
|
99
|
+
self.transformer_layers = []
|
100
|
+
for i in range(num_layers):
|
101
|
+
layer = FalconTransformerDecoder(
|
102
|
+
num_attention_heads=num_attention_heads,
|
103
|
+
intermediate_dim=intermediate_dim,
|
104
|
+
attention_dropout_rate=attention_dropout_rate,
|
105
|
+
feedforward_dropout_rate=feedforward_dropout_rate,
|
106
|
+
dtype=dtype,
|
107
|
+
name=f"transformer_layer_{i}",
|
108
|
+
)
|
109
|
+
self.transformer_layers.append(layer)
|
110
|
+
|
111
|
+
self.final_layernorm = keras.layers.LayerNormalization(
|
112
|
+
epsilon=layer_norm_epsilon,
|
113
|
+
dtype=dtype,
|
114
|
+
name="final_layernorm",
|
115
|
+
)
|
116
|
+
|
117
|
+
# === Functional Model ===
|
118
|
+
token_ids = keras.Input(shape=(None,), dtype="int32", name="token_ids")
|
119
|
+
padding_mask = keras.Input(
|
120
|
+
shape=(None,), dtype="int32", name="padding_mask"
|
121
|
+
)
|
122
|
+
# Embed Tokens.
|
123
|
+
x = self.token_embedding(token_ids)
|
124
|
+
|
125
|
+
# Apply successive transformer decoder blocks.
|
126
|
+
for transformer_layer in self.transformer_layers:
|
127
|
+
x = transformer_layer(inputs=x, decoder_padding_mask=padding_mask)
|
128
|
+
sequence_output = self.final_layernorm(x)
|
129
|
+
|
130
|
+
super().__init__(
|
131
|
+
inputs={
|
132
|
+
"token_ids": token_ids,
|
133
|
+
"padding_mask": padding_mask,
|
134
|
+
},
|
135
|
+
outputs=sequence_output,
|
136
|
+
dtype=dtype,
|
137
|
+
**kwargs,
|
138
|
+
)
|
139
|
+
|
140
|
+
# === Config ===
|
141
|
+
self.vocabulary_size = vocabulary_size
|
142
|
+
self.num_layers = num_layers
|
143
|
+
self.num_attention_heads = num_attention_heads
|
144
|
+
self.hidden_dim = hidden_dim
|
145
|
+
self.intermediate_dim = intermediate_dim
|
146
|
+
self.attention_dropout_rate = attention_dropout_rate
|
147
|
+
self.feedforward_dropout_rate = feedforward_dropout_rate
|
148
|
+
self.layer_norm_epsilon = layer_norm_epsilon
|
149
|
+
|
150
|
+
def get_config(self):
|
151
|
+
config = super().get_config()
|
152
|
+
config.update(
|
153
|
+
{
|
154
|
+
"vocabulary_size": self.vocabulary_size,
|
155
|
+
"num_layers": self.num_layers,
|
156
|
+
"num_attention_heads": self.num_attention_heads,
|
157
|
+
"hidden_dim": self.hidden_dim,
|
158
|
+
"intermediate_dim": self.intermediate_dim,
|
159
|
+
"attention_dropout_rate": self.attention_dropout_rate,
|
160
|
+
"feedforward_dropout_rate": self.feedforward_dropout_rate,
|
161
|
+
"layer_norm_epsilon": self.layer_norm_epsilon,
|
162
|
+
}
|
163
|
+
)
|
164
|
+
return config
|