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.
Files changed (297) hide show
  1. keras_hub/__init__.py +52 -0
  2. keras_hub/api/__init__.py +27 -0
  3. keras_hub/api/layers/__init__.py +47 -0
  4. keras_hub/api/metrics/__init__.py +24 -0
  5. keras_hub/api/models/__init__.py +249 -0
  6. keras_hub/api/samplers/__init__.py +29 -0
  7. keras_hub/api/tokenizers/__init__.py +35 -0
  8. keras_hub/src/__init__.py +13 -0
  9. keras_hub/src/api_export.py +53 -0
  10. keras_hub/src/layers/__init__.py +13 -0
  11. keras_hub/src/layers/modeling/__init__.py +13 -0
  12. keras_hub/src/layers/modeling/alibi_bias.py +143 -0
  13. keras_hub/src/layers/modeling/cached_multi_head_attention.py +137 -0
  14. keras_hub/src/layers/modeling/f_net_encoder.py +200 -0
  15. keras_hub/src/layers/modeling/masked_lm_head.py +239 -0
  16. keras_hub/src/layers/modeling/position_embedding.py +123 -0
  17. keras_hub/src/layers/modeling/reversible_embedding.py +311 -0
  18. keras_hub/src/layers/modeling/rotary_embedding.py +169 -0
  19. keras_hub/src/layers/modeling/sine_position_encoding.py +108 -0
  20. keras_hub/src/layers/modeling/token_and_position_embedding.py +150 -0
  21. keras_hub/src/layers/modeling/transformer_decoder.py +496 -0
  22. keras_hub/src/layers/modeling/transformer_encoder.py +262 -0
  23. keras_hub/src/layers/modeling/transformer_layer_utils.py +106 -0
  24. keras_hub/src/layers/preprocessing/__init__.py +13 -0
  25. keras_hub/src/layers/preprocessing/masked_lm_mask_generator.py +220 -0
  26. keras_hub/src/layers/preprocessing/multi_segment_packer.py +319 -0
  27. keras_hub/src/layers/preprocessing/preprocessing_layer.py +62 -0
  28. keras_hub/src/layers/preprocessing/random_deletion.py +271 -0
  29. keras_hub/src/layers/preprocessing/random_swap.py +267 -0
  30. keras_hub/src/layers/preprocessing/start_end_packer.py +219 -0
  31. keras_hub/src/metrics/__init__.py +13 -0
  32. keras_hub/src/metrics/bleu.py +394 -0
  33. keras_hub/src/metrics/edit_distance.py +197 -0
  34. keras_hub/src/metrics/perplexity.py +181 -0
  35. keras_hub/src/metrics/rouge_base.py +204 -0
  36. keras_hub/src/metrics/rouge_l.py +97 -0
  37. keras_hub/src/metrics/rouge_n.py +125 -0
  38. keras_hub/src/models/__init__.py +13 -0
  39. keras_hub/src/models/albert/__init__.py +20 -0
  40. keras_hub/src/models/albert/albert_backbone.py +267 -0
  41. keras_hub/src/models/albert/albert_classifier.py +202 -0
  42. keras_hub/src/models/albert/albert_masked_lm.py +129 -0
  43. keras_hub/src/models/albert/albert_masked_lm_preprocessor.py +194 -0
  44. keras_hub/src/models/albert/albert_preprocessor.py +206 -0
  45. keras_hub/src/models/albert/albert_presets.py +70 -0
  46. keras_hub/src/models/albert/albert_tokenizer.py +119 -0
  47. keras_hub/src/models/backbone.py +311 -0
  48. keras_hub/src/models/bart/__init__.py +20 -0
  49. keras_hub/src/models/bart/bart_backbone.py +261 -0
  50. keras_hub/src/models/bart/bart_preprocessor.py +276 -0
  51. keras_hub/src/models/bart/bart_presets.py +74 -0
  52. keras_hub/src/models/bart/bart_seq_2_seq_lm.py +490 -0
  53. keras_hub/src/models/bart/bart_seq_2_seq_lm_preprocessor.py +262 -0
  54. keras_hub/src/models/bart/bart_tokenizer.py +124 -0
  55. keras_hub/src/models/bert/__init__.py +23 -0
  56. keras_hub/src/models/bert/bert_backbone.py +227 -0
  57. keras_hub/src/models/bert/bert_classifier.py +183 -0
  58. keras_hub/src/models/bert/bert_masked_lm.py +131 -0
  59. keras_hub/src/models/bert/bert_masked_lm_preprocessor.py +198 -0
  60. keras_hub/src/models/bert/bert_preprocessor.py +184 -0
  61. keras_hub/src/models/bert/bert_presets.py +147 -0
  62. keras_hub/src/models/bert/bert_tokenizer.py +112 -0
  63. keras_hub/src/models/bloom/__init__.py +20 -0
  64. keras_hub/src/models/bloom/bloom_attention.py +186 -0
  65. keras_hub/src/models/bloom/bloom_backbone.py +173 -0
  66. keras_hub/src/models/bloom/bloom_causal_lm.py +298 -0
  67. keras_hub/src/models/bloom/bloom_causal_lm_preprocessor.py +176 -0
  68. keras_hub/src/models/bloom/bloom_decoder.py +206 -0
  69. keras_hub/src/models/bloom/bloom_preprocessor.py +185 -0
  70. keras_hub/src/models/bloom/bloom_presets.py +121 -0
  71. keras_hub/src/models/bloom/bloom_tokenizer.py +116 -0
  72. keras_hub/src/models/causal_lm.py +383 -0
  73. keras_hub/src/models/classifier.py +109 -0
  74. keras_hub/src/models/csp_darknet/__init__.py +13 -0
  75. keras_hub/src/models/csp_darknet/csp_darknet_backbone.py +410 -0
  76. keras_hub/src/models/csp_darknet/csp_darknet_image_classifier.py +133 -0
  77. keras_hub/src/models/deberta_v3/__init__.py +24 -0
  78. keras_hub/src/models/deberta_v3/deberta_v3_backbone.py +210 -0
  79. keras_hub/src/models/deberta_v3/deberta_v3_classifier.py +228 -0
  80. keras_hub/src/models/deberta_v3/deberta_v3_masked_lm.py +135 -0
  81. keras_hub/src/models/deberta_v3/deberta_v3_masked_lm_preprocessor.py +191 -0
  82. keras_hub/src/models/deberta_v3/deberta_v3_preprocessor.py +206 -0
  83. keras_hub/src/models/deberta_v3/deberta_v3_presets.py +82 -0
  84. keras_hub/src/models/deberta_v3/deberta_v3_tokenizer.py +155 -0
  85. keras_hub/src/models/deberta_v3/disentangled_attention_encoder.py +227 -0
  86. keras_hub/src/models/deberta_v3/disentangled_self_attention.py +412 -0
  87. keras_hub/src/models/deberta_v3/relative_embedding.py +94 -0
  88. keras_hub/src/models/densenet/__init__.py +13 -0
  89. keras_hub/src/models/densenet/densenet_backbone.py +210 -0
  90. keras_hub/src/models/densenet/densenet_image_classifier.py +131 -0
  91. keras_hub/src/models/distil_bert/__init__.py +26 -0
  92. keras_hub/src/models/distil_bert/distil_bert_backbone.py +187 -0
  93. keras_hub/src/models/distil_bert/distil_bert_classifier.py +208 -0
  94. keras_hub/src/models/distil_bert/distil_bert_masked_lm.py +137 -0
  95. keras_hub/src/models/distil_bert/distil_bert_masked_lm_preprocessor.py +194 -0
  96. keras_hub/src/models/distil_bert/distil_bert_preprocessor.py +175 -0
  97. keras_hub/src/models/distil_bert/distil_bert_presets.py +57 -0
  98. keras_hub/src/models/distil_bert/distil_bert_tokenizer.py +114 -0
  99. keras_hub/src/models/electra/__init__.py +20 -0
  100. keras_hub/src/models/electra/electra_backbone.py +247 -0
  101. keras_hub/src/models/electra/electra_preprocessor.py +154 -0
  102. keras_hub/src/models/electra/electra_presets.py +95 -0
  103. keras_hub/src/models/electra/electra_tokenizer.py +104 -0
  104. keras_hub/src/models/f_net/__init__.py +20 -0
  105. keras_hub/src/models/f_net/f_net_backbone.py +236 -0
  106. keras_hub/src/models/f_net/f_net_classifier.py +154 -0
  107. keras_hub/src/models/f_net/f_net_masked_lm.py +132 -0
  108. keras_hub/src/models/f_net/f_net_masked_lm_preprocessor.py +196 -0
  109. keras_hub/src/models/f_net/f_net_preprocessor.py +177 -0
  110. keras_hub/src/models/f_net/f_net_presets.py +43 -0
  111. keras_hub/src/models/f_net/f_net_tokenizer.py +95 -0
  112. keras_hub/src/models/falcon/__init__.py +20 -0
  113. keras_hub/src/models/falcon/falcon_attention.py +156 -0
  114. keras_hub/src/models/falcon/falcon_backbone.py +164 -0
  115. keras_hub/src/models/falcon/falcon_causal_lm.py +291 -0
  116. keras_hub/src/models/falcon/falcon_causal_lm_preprocessor.py +173 -0
  117. keras_hub/src/models/falcon/falcon_preprocessor.py +187 -0
  118. keras_hub/src/models/falcon/falcon_presets.py +30 -0
  119. keras_hub/src/models/falcon/falcon_tokenizer.py +110 -0
  120. keras_hub/src/models/falcon/falcon_transformer_decoder.py +255 -0
  121. keras_hub/src/models/feature_pyramid_backbone.py +73 -0
  122. keras_hub/src/models/gemma/__init__.py +20 -0
  123. keras_hub/src/models/gemma/gemma_attention.py +250 -0
  124. keras_hub/src/models/gemma/gemma_backbone.py +316 -0
  125. keras_hub/src/models/gemma/gemma_causal_lm.py +448 -0
  126. keras_hub/src/models/gemma/gemma_causal_lm_preprocessor.py +167 -0
  127. keras_hub/src/models/gemma/gemma_decoder_block.py +241 -0
  128. keras_hub/src/models/gemma/gemma_preprocessor.py +191 -0
  129. keras_hub/src/models/gemma/gemma_presets.py +248 -0
  130. keras_hub/src/models/gemma/gemma_tokenizer.py +103 -0
  131. keras_hub/src/models/gemma/rms_normalization.py +40 -0
  132. keras_hub/src/models/gpt2/__init__.py +20 -0
  133. keras_hub/src/models/gpt2/gpt2_backbone.py +199 -0
  134. keras_hub/src/models/gpt2/gpt2_causal_lm.py +437 -0
  135. keras_hub/src/models/gpt2/gpt2_causal_lm_preprocessor.py +173 -0
  136. keras_hub/src/models/gpt2/gpt2_preprocessor.py +187 -0
  137. keras_hub/src/models/gpt2/gpt2_presets.py +82 -0
  138. keras_hub/src/models/gpt2/gpt2_tokenizer.py +110 -0
  139. keras_hub/src/models/gpt_neo_x/__init__.py +13 -0
  140. keras_hub/src/models/gpt_neo_x/gpt_neo_x_attention.py +251 -0
  141. keras_hub/src/models/gpt_neo_x/gpt_neo_x_backbone.py +175 -0
  142. keras_hub/src/models/gpt_neo_x/gpt_neo_x_causal_lm.py +201 -0
  143. keras_hub/src/models/gpt_neo_x/gpt_neo_x_causal_lm_preprocessor.py +141 -0
  144. keras_hub/src/models/gpt_neo_x/gpt_neo_x_decoder.py +258 -0
  145. keras_hub/src/models/gpt_neo_x/gpt_neo_x_preprocessor.py +145 -0
  146. keras_hub/src/models/gpt_neo_x/gpt_neo_x_tokenizer.py +88 -0
  147. keras_hub/src/models/image_classifier.py +90 -0
  148. keras_hub/src/models/llama/__init__.py +20 -0
  149. keras_hub/src/models/llama/llama_attention.py +225 -0
  150. keras_hub/src/models/llama/llama_backbone.py +188 -0
  151. keras_hub/src/models/llama/llama_causal_lm.py +327 -0
  152. keras_hub/src/models/llama/llama_causal_lm_preprocessor.py +170 -0
  153. keras_hub/src/models/llama/llama_decoder.py +246 -0
  154. keras_hub/src/models/llama/llama_layernorm.py +48 -0
  155. keras_hub/src/models/llama/llama_preprocessor.py +189 -0
  156. keras_hub/src/models/llama/llama_presets.py +80 -0
  157. keras_hub/src/models/llama/llama_tokenizer.py +84 -0
  158. keras_hub/src/models/llama3/__init__.py +20 -0
  159. keras_hub/src/models/llama3/llama3_backbone.py +84 -0
  160. keras_hub/src/models/llama3/llama3_causal_lm.py +46 -0
  161. keras_hub/src/models/llama3/llama3_causal_lm_preprocessor.py +173 -0
  162. keras_hub/src/models/llama3/llama3_preprocessor.py +21 -0
  163. keras_hub/src/models/llama3/llama3_presets.py +69 -0
  164. keras_hub/src/models/llama3/llama3_tokenizer.py +63 -0
  165. keras_hub/src/models/masked_lm.py +101 -0
  166. keras_hub/src/models/mistral/__init__.py +20 -0
  167. keras_hub/src/models/mistral/mistral_attention.py +238 -0
  168. keras_hub/src/models/mistral/mistral_backbone.py +203 -0
  169. keras_hub/src/models/mistral/mistral_causal_lm.py +328 -0
  170. keras_hub/src/models/mistral/mistral_causal_lm_preprocessor.py +175 -0
  171. keras_hub/src/models/mistral/mistral_layer_norm.py +48 -0
  172. keras_hub/src/models/mistral/mistral_preprocessor.py +190 -0
  173. keras_hub/src/models/mistral/mistral_presets.py +48 -0
  174. keras_hub/src/models/mistral/mistral_tokenizer.py +82 -0
  175. keras_hub/src/models/mistral/mistral_transformer_decoder.py +265 -0
  176. keras_hub/src/models/mix_transformer/__init__.py +13 -0
  177. keras_hub/src/models/mix_transformer/mix_transformer_backbone.py +181 -0
  178. keras_hub/src/models/mix_transformer/mix_transformer_classifier.py +133 -0
  179. keras_hub/src/models/mix_transformer/mix_transformer_layers.py +300 -0
  180. keras_hub/src/models/opt/__init__.py +20 -0
  181. keras_hub/src/models/opt/opt_backbone.py +173 -0
  182. keras_hub/src/models/opt/opt_causal_lm.py +301 -0
  183. keras_hub/src/models/opt/opt_causal_lm_preprocessor.py +177 -0
  184. keras_hub/src/models/opt/opt_preprocessor.py +188 -0
  185. keras_hub/src/models/opt/opt_presets.py +72 -0
  186. keras_hub/src/models/opt/opt_tokenizer.py +116 -0
  187. keras_hub/src/models/pali_gemma/__init__.py +23 -0
  188. keras_hub/src/models/pali_gemma/pali_gemma_backbone.py +277 -0
  189. keras_hub/src/models/pali_gemma/pali_gemma_causal_lm.py +313 -0
  190. keras_hub/src/models/pali_gemma/pali_gemma_causal_lm_preprocessor.py +147 -0
  191. keras_hub/src/models/pali_gemma/pali_gemma_decoder_block.py +160 -0
  192. keras_hub/src/models/pali_gemma/pali_gemma_presets.py +78 -0
  193. keras_hub/src/models/pali_gemma/pali_gemma_tokenizer.py +79 -0
  194. keras_hub/src/models/pali_gemma/pali_gemma_vit.py +566 -0
  195. keras_hub/src/models/phi3/__init__.py +20 -0
  196. keras_hub/src/models/phi3/phi3_attention.py +260 -0
  197. keras_hub/src/models/phi3/phi3_backbone.py +224 -0
  198. keras_hub/src/models/phi3/phi3_causal_lm.py +218 -0
  199. keras_hub/src/models/phi3/phi3_causal_lm_preprocessor.py +173 -0
  200. keras_hub/src/models/phi3/phi3_decoder.py +260 -0
  201. keras_hub/src/models/phi3/phi3_layernorm.py +48 -0
  202. keras_hub/src/models/phi3/phi3_preprocessor.py +190 -0
  203. keras_hub/src/models/phi3/phi3_presets.py +50 -0
  204. keras_hub/src/models/phi3/phi3_rotary_embedding.py +137 -0
  205. keras_hub/src/models/phi3/phi3_tokenizer.py +94 -0
  206. keras_hub/src/models/preprocessor.py +207 -0
  207. keras_hub/src/models/resnet/__init__.py +13 -0
  208. keras_hub/src/models/resnet/resnet_backbone.py +612 -0
  209. keras_hub/src/models/resnet/resnet_image_classifier.py +136 -0
  210. keras_hub/src/models/roberta/__init__.py +20 -0
  211. keras_hub/src/models/roberta/roberta_backbone.py +184 -0
  212. keras_hub/src/models/roberta/roberta_classifier.py +209 -0
  213. keras_hub/src/models/roberta/roberta_masked_lm.py +136 -0
  214. keras_hub/src/models/roberta/roberta_masked_lm_preprocessor.py +198 -0
  215. keras_hub/src/models/roberta/roberta_preprocessor.py +192 -0
  216. keras_hub/src/models/roberta/roberta_presets.py +43 -0
  217. keras_hub/src/models/roberta/roberta_tokenizer.py +132 -0
  218. keras_hub/src/models/seq_2_seq_lm.py +54 -0
  219. keras_hub/src/models/t5/__init__.py +20 -0
  220. keras_hub/src/models/t5/t5_backbone.py +261 -0
  221. keras_hub/src/models/t5/t5_layer_norm.py +35 -0
  222. keras_hub/src/models/t5/t5_multi_head_attention.py +324 -0
  223. keras_hub/src/models/t5/t5_presets.py +95 -0
  224. keras_hub/src/models/t5/t5_tokenizer.py +100 -0
  225. keras_hub/src/models/t5/t5_transformer_layer.py +178 -0
  226. keras_hub/src/models/task.py +419 -0
  227. keras_hub/src/models/vgg/__init__.py +13 -0
  228. keras_hub/src/models/vgg/vgg_backbone.py +158 -0
  229. keras_hub/src/models/vgg/vgg_image_classifier.py +124 -0
  230. keras_hub/src/models/vit_det/__init__.py +13 -0
  231. keras_hub/src/models/vit_det/vit_det_backbone.py +204 -0
  232. keras_hub/src/models/vit_det/vit_layers.py +565 -0
  233. keras_hub/src/models/whisper/__init__.py +20 -0
  234. keras_hub/src/models/whisper/whisper_audio_feature_extractor.py +260 -0
  235. keras_hub/src/models/whisper/whisper_backbone.py +305 -0
  236. keras_hub/src/models/whisper/whisper_cached_multi_head_attention.py +153 -0
  237. keras_hub/src/models/whisper/whisper_decoder.py +141 -0
  238. keras_hub/src/models/whisper/whisper_encoder.py +106 -0
  239. keras_hub/src/models/whisper/whisper_preprocessor.py +326 -0
  240. keras_hub/src/models/whisper/whisper_presets.py +148 -0
  241. keras_hub/src/models/whisper/whisper_tokenizer.py +163 -0
  242. keras_hub/src/models/xlm_roberta/__init__.py +26 -0
  243. keras_hub/src/models/xlm_roberta/xlm_roberta_backbone.py +81 -0
  244. keras_hub/src/models/xlm_roberta/xlm_roberta_classifier.py +225 -0
  245. keras_hub/src/models/xlm_roberta/xlm_roberta_masked_lm.py +141 -0
  246. keras_hub/src/models/xlm_roberta/xlm_roberta_masked_lm_preprocessor.py +195 -0
  247. keras_hub/src/models/xlm_roberta/xlm_roberta_preprocessor.py +205 -0
  248. keras_hub/src/models/xlm_roberta/xlm_roberta_presets.py +43 -0
  249. keras_hub/src/models/xlm_roberta/xlm_roberta_tokenizer.py +191 -0
  250. keras_hub/src/models/xlnet/__init__.py +13 -0
  251. keras_hub/src/models/xlnet/relative_attention.py +459 -0
  252. keras_hub/src/models/xlnet/xlnet_backbone.py +222 -0
  253. keras_hub/src/models/xlnet/xlnet_content_and_query_embedding.py +133 -0
  254. keras_hub/src/models/xlnet/xlnet_encoder.py +378 -0
  255. keras_hub/src/samplers/__init__.py +13 -0
  256. keras_hub/src/samplers/beam_sampler.py +207 -0
  257. keras_hub/src/samplers/contrastive_sampler.py +231 -0
  258. keras_hub/src/samplers/greedy_sampler.py +50 -0
  259. keras_hub/src/samplers/random_sampler.py +77 -0
  260. keras_hub/src/samplers/sampler.py +237 -0
  261. keras_hub/src/samplers/serialization.py +97 -0
  262. keras_hub/src/samplers/top_k_sampler.py +92 -0
  263. keras_hub/src/samplers/top_p_sampler.py +113 -0
  264. keras_hub/src/tests/__init__.py +13 -0
  265. keras_hub/src/tests/test_case.py +608 -0
  266. keras_hub/src/tokenizers/__init__.py +13 -0
  267. keras_hub/src/tokenizers/byte_pair_tokenizer.py +638 -0
  268. keras_hub/src/tokenizers/byte_tokenizer.py +299 -0
  269. keras_hub/src/tokenizers/sentence_piece_tokenizer.py +267 -0
  270. keras_hub/src/tokenizers/sentence_piece_tokenizer_trainer.py +150 -0
  271. keras_hub/src/tokenizers/tokenizer.py +235 -0
  272. keras_hub/src/tokenizers/unicode_codepoint_tokenizer.py +355 -0
  273. keras_hub/src/tokenizers/word_piece_tokenizer.py +544 -0
  274. keras_hub/src/tokenizers/word_piece_tokenizer_trainer.py +176 -0
  275. keras_hub/src/utils/__init__.py +13 -0
  276. keras_hub/src/utils/keras_utils.py +130 -0
  277. keras_hub/src/utils/pipeline_model.py +293 -0
  278. keras_hub/src/utils/preset_utils.py +621 -0
  279. keras_hub/src/utils/python_utils.py +21 -0
  280. keras_hub/src/utils/tensor_utils.py +206 -0
  281. keras_hub/src/utils/timm/__init__.py +13 -0
  282. keras_hub/src/utils/timm/convert.py +37 -0
  283. keras_hub/src/utils/timm/convert_resnet.py +171 -0
  284. keras_hub/src/utils/transformers/__init__.py +13 -0
  285. keras_hub/src/utils/transformers/convert.py +101 -0
  286. keras_hub/src/utils/transformers/convert_bert.py +173 -0
  287. keras_hub/src/utils/transformers/convert_distilbert.py +184 -0
  288. keras_hub/src/utils/transformers/convert_gemma.py +187 -0
  289. keras_hub/src/utils/transformers/convert_gpt2.py +186 -0
  290. keras_hub/src/utils/transformers/convert_llama3.py +136 -0
  291. keras_hub/src/utils/transformers/convert_pali_gemma.py +303 -0
  292. keras_hub/src/utils/transformers/safetensor_utils.py +97 -0
  293. keras_hub/src/version_utils.py +23 -0
  294. keras_hub_nightly-0.15.0.dev20240823171555.dist-info/METADATA +34 -0
  295. keras_hub_nightly-0.15.0.dev20240823171555.dist-info/RECORD +297 -0
  296. keras_hub_nightly-0.15.0.dev20240823171555.dist-info/WHEEL +5 -0
  297. keras_hub_nightly-0.15.0.dev20240823171555.dist-info/top_level.txt +1 -0
@@ -0,0 +1,154 @@
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.models.classifier import Classifier
20
+ from keras_hub.src.models.f_net.f_net_backbone import FNetBackbone
21
+ from keras_hub.src.models.f_net.f_net_backbone import f_net_kernel_initializer
22
+ from keras_hub.src.models.f_net.f_net_preprocessor import FNetPreprocessor
23
+
24
+
25
+ @keras_hub_export("keras_hub.models.FNetClassifier")
26
+ class FNetClassifier(Classifier):
27
+ """An end-to-end f_net model for classification tasks.
28
+
29
+ This model attaches a classification head to a
30
+ `keras_hub.model.FNetBackbone` instance, mapping from the backbone outputs
31
+ to logits suitable for a classification task. For usage of this model with
32
+ pre-trained weights, use the `from_preset()` constructor.
33
+
34
+ This model can optionally be configured with a `preprocessor` layer, in
35
+ which case it will automatically apply preprocessing to raw inputs during
36
+ `fit()`, `predict()`, and `evaluate()`. This is done by default when
37
+ creating the model with `from_preset()`.
38
+
39
+ Disclaimer: Pre-trained models are provided on an "as is" basis, without
40
+ warranties or conditions of any kind.
41
+
42
+ Args:
43
+ backbone: A `keras_hub.models.FNetBackbone` instance.
44
+ num_classes: int. Number of classes to predict.
45
+ preprocessor: A `keras_hub.models.FNetPreprocessor` or `None`. If
46
+ `None`, this model will not apply preprocessing, and inputs should
47
+ be preprocessed before calling the model.
48
+ activation: Optional `str` or callable. The
49
+ activation function to use on the model outputs. Set
50
+ `activation="softmax"` to return output probabilities.
51
+ Defaults to `None`.
52
+ hidden_dim: int. The size of the pooler layer.
53
+ dropout: float. The dropout probability value, applied after the dense
54
+ layer.
55
+
56
+ Examples:
57
+
58
+ Raw string data.
59
+ ```python
60
+ features = ["The quick brown fox jumped.", "I forgot my homework."]
61
+ labels = [0, 3]
62
+
63
+ # Pretrained classifier.
64
+ classifier = keras_hub.models.FNetClassifier.from_preset(
65
+ "f_net_base_en",
66
+ num_classes=4,
67
+ )
68
+ classifier.fit(x=features, y=labels, batch_size=2)
69
+ classifier.predict(x=features, batch_size=2)
70
+
71
+ # Re-compile (e.g., with a new learning rate).
72
+ classifier.compile(
73
+ loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
74
+ optimizer=keras.optimizers.Adam(5e-5),
75
+ jit_compile=True,
76
+ )
77
+ # Access backbone programmatically (e.g., to change `trainable`).
78
+ classifier.backbone.trainable = False
79
+ # Fit again.
80
+ classifier.fit(x=features, y=labels, batch_size=2)
81
+ ```
82
+
83
+ Preprocessed integer data.
84
+ ```python
85
+ features = {
86
+ "token_ids": np.ones(shape=(2, 12), dtype="int32"),
87
+ "segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
88
+ }
89
+ labels = [0, 3]
90
+
91
+ # Pretrained classifier without preprocessing.
92
+ classifier = keras_hub.models.FNetClassifier.from_preset(
93
+ "f_net_base_en",
94
+ num_classes=4,
95
+ preprocessor=None,
96
+ )
97
+ classifier.fit(x=features, y=labels, batch_size=2)
98
+ ```
99
+ """
100
+
101
+ backbone_cls = FNetBackbone
102
+ preprocessor_cls = FNetPreprocessor
103
+
104
+ def __init__(
105
+ self,
106
+ backbone,
107
+ num_classes,
108
+ preprocessor=None,
109
+ activation=None,
110
+ dropout=0.1,
111
+ **kwargs,
112
+ ):
113
+ # === Layers ===
114
+ self.backbone = backbone
115
+ self.preprocessor = preprocessor
116
+ self.output_dropout = keras.layers.Dropout(
117
+ dropout,
118
+ dtype=backbone.dtype_policy,
119
+ name="output_dropout",
120
+ )
121
+ self.output_dense = keras.layers.Dense(
122
+ num_classes,
123
+ kernel_initializer=f_net_kernel_initializer(),
124
+ activation=activation,
125
+ dtype=backbone.dtype_policy,
126
+ name="logits",
127
+ )
128
+
129
+ # === Functional Model ===
130
+ inputs = backbone.input
131
+ pooled = backbone(inputs)["pooled_output"]
132
+ pooled = self.output_dropout(pooled)
133
+ outputs = self.output_dense(pooled)
134
+ super().__init__(
135
+ inputs=inputs,
136
+ outputs=outputs,
137
+ **kwargs,
138
+ )
139
+
140
+ # === Config ===
141
+ self.num_classes = num_classes
142
+ self.activation = keras.activations.get(activation)
143
+ self.dropout = dropout
144
+
145
+ def get_config(self):
146
+ config = super().get_config()
147
+ config.update(
148
+ {
149
+ "num_classes": self.num_classes,
150
+ "dropout": self.dropout,
151
+ "activation": keras.activations.serialize(self.activation),
152
+ }
153
+ )
154
+ return config
@@ -0,0 +1,132 @@
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.modeling.masked_lm_head import MaskedLMHead
20
+ from keras_hub.src.models.f_net.f_net_backbone import FNetBackbone
21
+ from keras_hub.src.models.f_net.f_net_backbone import f_net_kernel_initializer
22
+ from keras_hub.src.models.f_net.f_net_masked_lm_preprocessor import (
23
+ FNetMaskedLMPreprocessor,
24
+ )
25
+ from keras_hub.src.models.masked_lm import MaskedLM
26
+
27
+
28
+ @keras_hub_export("keras_hub.models.FNetMaskedLM")
29
+ class FNetMaskedLM(MaskedLM):
30
+ """An end-to-end FNet model for the masked language modeling task.
31
+
32
+ This model will train FNet on a masked language modeling task.
33
+ The model will predict labels for a number of masked tokens in the
34
+ input data. For usage of this model with pre-trained weights, see the
35
+ `from_preset()` constructor.
36
+
37
+ This model can optionally be configured with a `preprocessor` layer, in
38
+ which case inputs can be raw string features during `fit()`, `predict()`,
39
+ and `evaluate()`. Inputs will be tokenized and dynamically masked during
40
+ training and evaluation. This is done by default when creating the model
41
+ with `from_preset()`.
42
+
43
+ Disclaimer: Pre-trained models are provided on an "as is" basis, without
44
+ warranties or conditions of any kind.
45
+
46
+ Args:
47
+ backbone: A `keras_hub.models.FNetBackbone` instance.
48
+ preprocessor: A `keras_hub.models.FNetMaskedLMPreprocessor` or
49
+ `None`. If `None`, this model will not apply preprocessing, and
50
+ inputs should be preprocessed before calling the model.
51
+
52
+ Examples:
53
+
54
+ Raw string data.
55
+ ```python
56
+
57
+ features = ["The quick brown fox jumped.", "I forgot my homework."]
58
+
59
+ # Pretrained language model.
60
+ masked_lm = keras_hub.models.FNetMaskedLM.from_preset(
61
+ "f_net_base_en",
62
+ )
63
+ masked_lm.fit(x=features, batch_size=2)
64
+
65
+ # Re-compile (e.g., with a new learning rate).
66
+ masked_lm.compile(
67
+ loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
68
+ optimizer=keras.optimizers.Adam(5e-5),
69
+ jit_compile=True,
70
+ )
71
+ # Access backbone programmatically (e.g., to change `trainable`).
72
+ masked_lm.backbone.trainable = False
73
+ # Fit again.
74
+ masked_lm.fit(x=features, batch_size=2)
75
+ ```
76
+
77
+ Preprocessed integer data.
78
+ ```python
79
+ # Create a preprocessed dataset where 0 is the mask token.
80
+ features = {
81
+ "token_ids": np.array([[1, 2, 0, 4, 0, 6, 7, 8]] * 2),
82
+ "segment_ids": np.array([[0, 0, 0, 1, 1, 1, 0, 0]] * 2),
83
+ "mask_positions": np.array([[2, 4]] * 2)
84
+ }
85
+ # Labels are the original masked values.
86
+ labels = [[3, 5]] * 2
87
+
88
+ masked_lm = keras_hub.models.FNetMaskedLM.from_preset(
89
+ "f_net_base_en",
90
+ preprocessor=None,
91
+ )
92
+ masked_lm.fit(x=features, y=labels, batch_size=2)
93
+ ```
94
+ """
95
+
96
+ backbone_cls = FNetBackbone
97
+ preprocessor_cls = FNetMaskedLMPreprocessor
98
+
99
+ def __init__(
100
+ self,
101
+ backbone,
102
+ preprocessor=None,
103
+ **kwargs,
104
+ ):
105
+ # === Layers ===
106
+ self.backbone = backbone
107
+ self.preprocessor = preprocessor
108
+ self.masked_lm_head = MaskedLMHead(
109
+ vocabulary_size=backbone.vocabulary_size,
110
+ token_embedding=backbone.token_embedding,
111
+ intermediate_activation="gelu",
112
+ kernel_initializer=f_net_kernel_initializer(),
113
+ dtype=backbone.dtype_policy,
114
+ name="mlm_head",
115
+ )
116
+
117
+ # === Functional Model ===
118
+ inputs = {
119
+ **backbone.input,
120
+ "mask_positions": keras.Input(
121
+ shape=(None,), dtype="int32", name="mask_positions"
122
+ ),
123
+ }
124
+ backbone_outputs = backbone(backbone.input)
125
+ outputs = self.masked_lm_head(
126
+ backbone_outputs["sequence_output"], inputs["mask_positions"]
127
+ )
128
+ super().__init__(
129
+ inputs=inputs,
130
+ outputs=outputs,
131
+ **kwargs,
132
+ )
@@ -0,0 +1,196 @@
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 absl import logging
17
+
18
+ from keras_hub.src.api_export import keras_hub_export
19
+ from keras_hub.src.layers.preprocessing.masked_lm_mask_generator import (
20
+ MaskedLMMaskGenerator,
21
+ )
22
+ from keras_hub.src.models.f_net.f_net_preprocessor import FNetPreprocessor
23
+
24
+
25
+ @keras_hub_export("keras_hub.models.FNetMaskedLMPreprocessor")
26
+ class FNetMaskedLMPreprocessor(FNetPreprocessor):
27
+ """FNet preprocessing for the masked language modeling task.
28
+
29
+ This preprocessing layer will prepare inputs for a masked language modeling
30
+ task. It is primarily intended for use with the
31
+ `keras_hub.models.FNetMaskedLM` task model. Preprocessing will occur in
32
+ multiple steps.
33
+
34
+ 1. Tokenize any number of input segments using the `tokenizer`.
35
+ 2. Pack the inputs together with the appropriate `"<s>"`, `"</s>"` and
36
+ `"<pad>"` tokens, i.e., adding a single `"<s>"` at the start of the
37
+ entire sequence, `"</s></s>"` between each segment,
38
+ and a `"</s>"` at the end of the entire sequence.
39
+ 3. Randomly select non-special tokens to mask, controlled by
40
+ `mask_selection_rate`.
41
+ 4. Construct a `(x, y, sample_weight)` tuple suitable for training with a
42
+ `keras_hub.models.FNetMaskedLM` task model.
43
+
44
+ Args:
45
+ tokenizer: A `keras_hub.models.FNetTokenizer` instance.
46
+ sequence_length: The length of the packed inputs.
47
+ mask_selection_rate: The probability an input token will be dynamically
48
+ masked.
49
+ mask_selection_length: The maximum number of masked tokens supported
50
+ by the layer.
51
+ mask_token_rate: float. `mask_token_rate` must be
52
+ between 0 and 1 which indicates how often the mask_token is
53
+ substituted for tokens selected for masking. Defaults to `0.8`.
54
+ random_token_rate: float. `random_token_rate` must be
55
+ between 0 and 1 which indicates how often a random token is
56
+ substituted for tokens selected for masking.
57
+ Note: mask_token_rate + random_token_rate <= 1, and for
58
+ (1 - mask_token_rate - random_token_rate), the token will not be
59
+ changed. Defaults to `0.1`.
60
+ truncate: string. The algorithm to truncate a list of batched segments
61
+ to fit within `sequence_length`. The value can be either
62
+ `round_robin` or `waterfall`:
63
+ - `"round_robin"`: Available space is assigned one token at a
64
+ time in a round-robin fashion to the inputs that still need
65
+ some, until the limit is reached.
66
+ - `"waterfall"`: The allocation of the budget is done using a
67
+ "waterfall" algorithm that allocates quota in a
68
+ left-to-right manner and fills up the buckets until we run
69
+ out of budget. It supports an arbitrary number of segments.
70
+
71
+ Examples:
72
+
73
+ Directly calling the layer on data.
74
+ ```python
75
+ # Load the preprocessor from a preset.
76
+ preprocessor = keras_hub.models.FNetMaskedLMPreprocessor.from_preset(
77
+ "f_net_base_en"
78
+ )
79
+
80
+ # Tokenize and mask a single sentence.
81
+ preprocessor("The quick brown fox jumped.")
82
+
83
+ # Tokenize and mask a batch of single sentences.
84
+ preprocessor(["The quick brown fox jumped.", "Call me Ishmael."])
85
+
86
+ # Tokenize and mask sentence pairs.
87
+ # In this case, always convert input to tensors before calling the layer.
88
+ first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
89
+ second = tf.constant(["The fox tripped.", "Oh look, a whale."])
90
+ preprocessor((first, second))
91
+ ```
92
+
93
+ Mapping with `tf.data.Dataset`.
94
+ ```python
95
+ preprocessor = keras_hub.models.FNetMaskedLMPreprocessor.from_preset(
96
+ "f_net_base_en"
97
+ )
98
+
99
+ first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
100
+ second = tf.constant(["The fox tripped.", "Oh look, a whale."])
101
+
102
+ # Map single sentences.
103
+ ds = tf.data.Dataset.from_tensor_slices(first)
104
+ ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
105
+
106
+ # Alternatively, you can create a preprocessor from your own vocabulary.
107
+ vocab_data = tf.data.Dataset.from_tensor_slices(
108
+ ["the quick brown fox", "the earth is round"]
109
+ )
110
+
111
+ # Map sentence pairs.
112
+ ds = tf.data.Dataset.from_tensor_slices((first, second))
113
+ # Watch out for tf.data's default unpacking of tuples here!
114
+ # Best to invoke the `preprocessor` directly in this case.
115
+ ds = ds.map(
116
+ lambda first, second: preprocessor(x=(first, second)),
117
+ num_parallel_calls=tf.data.AUTOTUNE,
118
+ )
119
+ ```
120
+ """
121
+
122
+ def __init__(
123
+ self,
124
+ tokenizer,
125
+ sequence_length=512,
126
+ truncate="round_robin",
127
+ mask_selection_rate=0.15,
128
+ mask_selection_length=96,
129
+ mask_token_rate=0.8,
130
+ random_token_rate=0.1,
131
+ **kwargs,
132
+ ):
133
+ super().__init__(
134
+ tokenizer,
135
+ sequence_length=sequence_length,
136
+ truncate=truncate,
137
+ **kwargs,
138
+ )
139
+ self.mask_selection_rate = mask_selection_rate
140
+ self.mask_selection_length = mask_selection_length
141
+ self.mask_token_rate = mask_token_rate
142
+ self.random_token_rate = random_token_rate
143
+ self.masker = None
144
+
145
+ def build(self, input_shape):
146
+ super().build(input_shape)
147
+ # Defer masker creation to `build()` so that we can be sure tokenizer
148
+ # assets have loaded when restoring a saved model.
149
+ self.masker = MaskedLMMaskGenerator(
150
+ mask_selection_rate=self.mask_selection_rate,
151
+ mask_selection_length=self.mask_selection_length,
152
+ mask_token_rate=self.mask_token_rate,
153
+ random_token_rate=self.random_token_rate,
154
+ vocabulary_size=self.tokenizer.vocabulary_size(),
155
+ mask_token_id=self.tokenizer.mask_token_id,
156
+ unselectable_token_ids=[
157
+ self.tokenizer.cls_token_id,
158
+ self.tokenizer.sep_token_id,
159
+ self.tokenizer.pad_token_id,
160
+ ],
161
+ )
162
+
163
+ def get_config(self):
164
+ config = super().get_config()
165
+ config.update(
166
+ {
167
+ "mask_selection_rate": self.mask_selection_rate,
168
+ "mask_selection_length": self.mask_selection_length,
169
+ "mask_token_rate": self.mask_token_rate,
170
+ "random_token_rate": self.random_token_rate,
171
+ }
172
+ )
173
+ return config
174
+
175
+ def call(self, x, y=None, sample_weight=None):
176
+ if y is not None or sample_weight is not None:
177
+ logging.warning(
178
+ f"{self.__class__.__name__} generates `y` and `sample_weight` "
179
+ "based on your input data, but your data already contains `y` "
180
+ "or `sample_weight`. Your `y` and `sample_weight` will be "
181
+ "ignored."
182
+ )
183
+ x = super().call(x)
184
+ token_ids, segment_ids = (
185
+ x["token_ids"],
186
+ x["segment_ids"],
187
+ )
188
+ masker_outputs = self.masker(token_ids)
189
+ x = {
190
+ "token_ids": masker_outputs["token_ids"],
191
+ "segment_ids": segment_ids,
192
+ "mask_positions": masker_outputs["mask_positions"],
193
+ }
194
+ y = masker_outputs["mask_ids"]
195
+ sample_weight = masker_outputs["mask_weights"]
196
+ return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)
@@ -0,0 +1,177 @@
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.multi_segment_packer import (
20
+ MultiSegmentPacker,
21
+ )
22
+ from keras_hub.src.models.f_net.f_net_tokenizer import FNetTokenizer
23
+ from keras_hub.src.models.preprocessor import Preprocessor
24
+ from keras_hub.src.utils.keras_utils import (
25
+ convert_inputs_to_list_of_tensor_segments,
26
+ )
27
+
28
+
29
+ @keras_hub_export("keras_hub.models.FNetPreprocessor")
30
+ class FNetPreprocessor(Preprocessor):
31
+ """An FNet preprocessing layer which tokenizes and packs inputs.
32
+
33
+ This preprocessing layer will do three things:
34
+
35
+ 1. Tokenize any number of input segments using the `tokenizer`.
36
+ 2. Pack the inputs together using a `keras_hub.layers.MultiSegmentPacker`.
37
+ with the appropriate `"[CLS]"`, `"[SEP]"` and `"<pad>"` tokens.
38
+ 3. Construct a dictionary with keys `"token_ids"`, and `"segment_ids"` that
39
+ can be passed directly to `keras_hub.models.FNetBackbone`.
40
+
41
+ This layer can be used directly with `tf.data.Dataset.map` to preprocess
42
+ string data in the `(x, y, sample_weight)` format used by
43
+ `keras.Model.fit`.
44
+
45
+ Args:
46
+ tokenizer: A `keras_hub.models.FNetTokenizer` instance.
47
+ sequence_length: The length of the packed inputs.
48
+ truncate: string. The algorithm to truncate a list of batched segments
49
+ to fit within `sequence_length`. The value can be either
50
+ `round_robin` or `waterfall`:
51
+ - `"round_robin"`: Available space is assigned one token at a
52
+ time in a round-robin fashion to the inputs that still need
53
+ some, until the limit is reached.
54
+ - `"waterfall"`: The allocation of the budget is done using a
55
+ "waterfall" algorithm that allocates quota in a
56
+ left-to-right manner and fills up the buckets until we run
57
+ out of budget. It supports an arbitrary number of segments.
58
+
59
+ Call arguments:
60
+ x: A tensor of single string sequences, or a tuple of multiple
61
+ tensor sequences to be packed together. Inputs may be batched or
62
+ unbatched. For single sequences, raw python inputs will be converted
63
+ to tensors. For multiple sequences, pass tensors directly.
64
+ y: Any label data. Will be passed through unaltered.
65
+ sample_weight: Any label weight data. Will be passed through unaltered.
66
+
67
+ Examples:
68
+
69
+ Directly calling the from_preset().
70
+ ```python
71
+ preprocessor = keras_hub.models.FNetPreprocessor.from_preset(
72
+ "f_net_base_en"
73
+ )
74
+
75
+ # Tokenize and pack a single sentence.
76
+ preprocessor("The quick brown fox jumped.")
77
+
78
+ # Tokenize and a batch of single sentences.
79
+ preprocessor(["The quick brown fox jumped.", "Call me Ishmael."])
80
+
81
+ # Preprocess a batch of sentence pairs.
82
+ # When handling multiple sequences, always convert to tensors first!
83
+ first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
84
+ second = tf.constant(["The fox tripped.", "Oh look, a whale."])
85
+ preprocessor((first, second))
86
+ ```
87
+
88
+ Mapping with `tf.data.Dataset`.
89
+ ```python
90
+ preprocessor = keras_hub.models.FNetPreprocessor.from_preset(
91
+ "f_net_base_en"
92
+ )
93
+ first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
94
+ second = tf.constant(["The fox tripped.", "Oh look, a whale."])
95
+ label = tf.constant([1, 1])
96
+
97
+ # Map labeled single sentences.
98
+ ds = tf.data.Dataset.from_tensor_slices((first, label))
99
+ ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
100
+
101
+ # Map unlabeled single sentences.
102
+ ds = tf.data.Dataset.from_tensor_slices(first)
103
+ ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
104
+
105
+ # Map labeled sentence pairs.
106
+ ds = tf.data.Dataset.from_tensor_slices(((first, second), label))
107
+ ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
108
+
109
+ # Map unlabeled sentence pairs.
110
+ ds = tf.data.Dataset.from_tensor_slices((first, second))
111
+
112
+ # Watch out for tf.data's default unpacking of tuples here!
113
+ # Best to invoke the `preprocessor` directly in this case.
114
+ ds = ds.map(
115
+ lambda first, second: preprocessor(x=(first, second)),
116
+ num_parallel_calls=tf.data.AUTOTUNE,
117
+ )
118
+ ```
119
+ """
120
+
121
+ tokenizer_cls = FNetTokenizer
122
+
123
+ def __init__(
124
+ self,
125
+ tokenizer,
126
+ sequence_length=512,
127
+ truncate="round_robin",
128
+ **kwargs,
129
+ ):
130
+ super().__init__(**kwargs)
131
+ self.tokenizer = tokenizer
132
+ self.packer = None
133
+ self.truncate = truncate
134
+ self.sequence_length = sequence_length
135
+
136
+ def build(self, input_shape):
137
+ # Defer packer creation to `build()` so that we can be sure tokenizer
138
+ # assets have loaded when restoring a saved model.
139
+ self.packer = MultiSegmentPacker(
140
+ start_value=self.tokenizer.cls_token_id,
141
+ end_value=self.tokenizer.sep_token_id,
142
+ pad_value=self.tokenizer.pad_token_id,
143
+ truncate=self.truncate,
144
+ sequence_length=self.sequence_length,
145
+ )
146
+ self.built = True
147
+
148
+ def get_config(self):
149
+ config = super().get_config()
150
+ config.update(
151
+ {
152
+ "sequence_length": self.sequence_length,
153
+ "truncate": self.truncate,
154
+ }
155
+ )
156
+ return config
157
+
158
+ def call(self, x, y=None, sample_weight=None):
159
+ x = convert_inputs_to_list_of_tensor_segments(x)
160
+ x = [self.tokenizer(segment) for segment in x]
161
+ token_ids, segment_ids = self.packer(x)
162
+ x = {
163
+ "token_ids": token_ids,
164
+ "segment_ids": segment_ids,
165
+ }
166
+ return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)
167
+
168
+ @property
169
+ def sequence_length(self):
170
+ """The padded length of model input sequences."""
171
+ return self._sequence_length
172
+
173
+ @sequence_length.setter
174
+ def sequence_length(self, value):
175
+ self._sequence_length = value
176
+ if self.packer is not None:
177
+ self.packer.sequence_length = value