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 +1,150 @@
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 io
16
+
17
+ try:
18
+ import tensorflow as tf
19
+ except ImportError:
20
+ raise ImportError(
21
+ "To use `keras_hub`, please install Tensorflow: `pip install tensorflow`. "
22
+ "The TensorFlow package is required for data preprocessing with any backend."
23
+ )
24
+
25
+ try:
26
+ import sentencepiece as spm
27
+ except ImportError:
28
+ spm = None
29
+
30
+ from keras_hub.src.api_export import keras_hub_export
31
+
32
+
33
+ @keras_hub_export("keras_hub.tokenizers.compute_sentence_piece_proto")
34
+ def compute_sentence_piece_proto(
35
+ data,
36
+ vocabulary_size,
37
+ model_type="unigram",
38
+ proto_output_file=None,
39
+ lowercase=False,
40
+ ):
41
+ r"""A utility to train a SentencePiece vocabulary.
42
+
43
+ Trains a SentencePiece vocabulary from an input dataset or a list of
44
+ filenames.
45
+
46
+ If `data` is a list of filenames, the file format is required to be plain
47
+ text files, and the text will be read in line by line during training.
48
+
49
+ Args:
50
+ data: A `tf.data.Dataset`, or a list of filenames.
51
+ vocabulary_size: int. The maximum size of a vocabulary to be trained.
52
+ model_type: str. The model algorithm must be one of
53
+ `"unigram"`, `"bpe"`, `"word"` or `"char"`. Defaults to `"unigram"`.
54
+ proto_output_file: str. If provided it will be used
55
+ as model_file which is passed to model_writer.
56
+ If `None`, the model_file will be `io.BytesIO` object.
57
+ Defaults to `None`.
58
+ lowercase: bool. If True, the input text will be
59
+ lowercased before tokenization. Defaults to `False`.
60
+
61
+ Returns:
62
+ A `bytes` object with a serialized SentencePiece proto or
63
+ `None` if proto_output_file if provided.
64
+
65
+ Examples:
66
+
67
+ Basic Usage (from Dataset).
68
+ >>> inputs = tf.data.Dataset.from_tensor_slices(["Drifting Along"])
69
+ >>> proto = keras_hub.tokenizers.compute_sentence_piece_proto(inputs, vocabulary_size=15)
70
+ >>> tokenizer = keras_hub.tokenizers.SentencePieceTokenizer(proto=proto)
71
+ >>> outputs = inputs.map(tokenizer)
72
+ >>> for output in outputs:
73
+ ... print(output)
74
+ tf.Tensor([ 4 8 12 5 9 14 5 6 13 4 7 10 11 6 13],
75
+ shape=(15,), dtype=int32)
76
+
77
+ Basic Usage (with files).
78
+ ``` python
79
+ with open("test.txt", "w+") as f: f.write("Drifting Along\n")
80
+ inputs = ["test.txt"]
81
+ proto = keras_hub.tokenizers.compute_sentence_piece_proto(
82
+ inputs, vocabulary_size=15, proto_output_file="model.spm")
83
+ tokenizer = keras_hub.tokenizers.SentencePieceTokenizer(proto="model.spm")
84
+ ds = tf.data.Dataset.from_tensor_slices(["the quick brown fox."])
85
+ ds = ds.map(tokenizer)
86
+ ```
87
+
88
+ Usage with lowercase
89
+ >>> inputs = tf.data.Dataset.from_tensor_slices(["Drifting Along"])
90
+ >>> proto = keras_hub.tokenizers.compute_sentence_piece_proto(
91
+ ... inputs, vocabulary_size=15, lowercase=True)
92
+ >>> tokenizer = keras_hub.tokenizers.SentencePieceTokenizer(proto=proto)
93
+ >>> outputs = inputs.map(tokenizer)
94
+ >>> for output in outputs:
95
+ ... print(output)
96
+ tf.Tensor([ 4 8 12 5 9 14 5 6 13 4 7 10 11 6 13],
97
+ shape=(15,), dtype=int32)
98
+ """
99
+
100
+ if spm is None:
101
+ raise ImportError(
102
+ f"{compute_sentence_piece_proto.__name__} requires the "
103
+ "`sentencepiece` package. Please install it with "
104
+ "`pip install sentencepiece`."
105
+ )
106
+
107
+ if not isinstance(data, (list, tuple, tf.data.Dataset)):
108
+ raise ValueError(
109
+ "The `data` argument must be either `tf.data.Dataset` or `tuple` or `list`. "
110
+ f"Received: type(data)={type(data)}."
111
+ )
112
+
113
+ if model_type not in ["unigram", "bpe", "word", "char"]:
114
+ raise ValueError(
115
+ "The `model_type` argument must be one of `unigram`, `bpe`, `word`"
116
+ f"or `char`. Received: model_type={model_type}."
117
+ )
118
+
119
+ model_writer = (
120
+ open(proto_output_file, "wb") if proto_output_file else io.BytesIO()
121
+ )
122
+ is_dataset = isinstance(data, tf.data.Dataset)
123
+ if is_dataset:
124
+ spm.SentencePieceTrainer.train(
125
+ sentence_iterator=data.as_numpy_iterator(),
126
+ model_writer=model_writer,
127
+ vocab_size=vocabulary_size,
128
+ model_type=model_type,
129
+ normalization_rule_name="nmt_nfkc_cf" if lowercase else "nmt_nfkc",
130
+ pad_id=0,
131
+ unk_id=1,
132
+ bos_id=2,
133
+ eos_id=3,
134
+ )
135
+ else:
136
+ spm.SentencePieceTrainer.train(
137
+ input=data,
138
+ model_writer=model_writer,
139
+ vocab_size=vocabulary_size,
140
+ model_type=model_type,
141
+ normalization_rule_name="nmt_nfkc_cf" if lowercase else "nmt_nfkc",
142
+ pad_id=0,
143
+ unk_id=1,
144
+ bos_id=2,
145
+ eos_id=3,
146
+ )
147
+ if proto_output_file:
148
+ model_writer.close()
149
+ else:
150
+ return model_writer.getvalue()
@@ -0,0 +1,235 @@
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 os
15
+
16
+ from keras_hub.src.api_export import keras_hub_export
17
+ from keras_hub.src.layers.preprocessing.preprocessing_layer import (
18
+ PreprocessingLayer,
19
+ )
20
+ from keras_hub.src.utils.preset_utils import TOKENIZER_ASSET_DIR
21
+ from keras_hub.src.utils.preset_utils import TOKENIZER_CONFIG_FILE
22
+ from keras_hub.src.utils.preset_utils import check_config_class
23
+ from keras_hub.src.utils.preset_utils import check_format
24
+ from keras_hub.src.utils.preset_utils import get_file
25
+ from keras_hub.src.utils.preset_utils import list_presets
26
+ from keras_hub.src.utils.preset_utils import list_subclasses
27
+ from keras_hub.src.utils.preset_utils import load_serialized_object
28
+ from keras_hub.src.utils.preset_utils import save_serialized_object
29
+ from keras_hub.src.utils.preset_utils import save_tokenizer_assets
30
+ from keras_hub.src.utils.python_utils import classproperty
31
+ from keras_hub.src.utils.transformers.convert import load_transformers_tokenizer
32
+
33
+
34
+ @keras_hub_export(
35
+ [
36
+ "keras_hub.models.Tokenizer",
37
+ "keras_hub.tokenizers.Tokenizer",
38
+ ]
39
+ )
40
+ class Tokenizer(PreprocessingLayer):
41
+ """A base class for tokenizer layers.
42
+
43
+ Tokenizers in the KerasHub library should all subclass this layer.
44
+ The class provides two core methods `tokenize()` and `detokenize()` for
45
+ going from plain text to sequences and back. A tokenizer is a subclass of
46
+ `keras.layers.Layer` and can be combined into a `keras.Model`.
47
+
48
+ Subclassers should always implement the `tokenize()` method, which will also
49
+ be the default when calling the layer directly on inputs.
50
+
51
+ Subclassers can optionally implement the `detokenize()` method if the
52
+ tokenization is reversible. Otherwise, this can be skipped.
53
+
54
+ Subclassers should implement `get_vocabulary()`, `vocabulary_size()`,
55
+ `token_to_id()` and `id_to_token()` if applicable. For some simple
56
+ "vocab free" tokenizers, such as a whitespace splitter show below, these
57
+ methods do not apply and can be skipped.
58
+
59
+ Example:
60
+
61
+ ```python
62
+ class WhitespaceSplitterTokenizer(keras_hub.tokenizers.Tokenizer):
63
+ def tokenize(self, inputs):
64
+ return tf.strings.split(inputs)
65
+
66
+ def detokenize(self, inputs):
67
+ return tf.strings.reduce_join(inputs, separator=" ", axis=-1)
68
+
69
+ tokenizer = WhitespaceSplitterTokenizer()
70
+
71
+ # Tokenize some inputs.
72
+ tokenizer.tokenize("This is a test")
73
+
74
+ # Shorthard for `tokenize()`.
75
+ tokenizer("This is a test")
76
+
77
+ # Detokenize some outputs.
78
+ tokenizer.detokenize(["This", "is", "a", "test"])
79
+ ```
80
+ """
81
+
82
+ def __init__(self, *args, **kwargs):
83
+ super().__init__(*args, **kwargs)
84
+ self.file_assets = None
85
+
86
+ def tokenize(self, inputs, *args, **kwargs):
87
+ """Transform input tensors of strings into output tokens.
88
+
89
+ Args:
90
+ inputs: Input tensor, or dict/list/tuple of input tensors.
91
+ *args: Additional positional arguments.
92
+ **kwargs: Additional keyword arguments.
93
+ """
94
+ raise NotImplementedError(
95
+ "No implementation of `tokenize()` was found for "
96
+ f"{self.__class__.__name__}. All tokenizers should implement "
97
+ "`tokenize()`."
98
+ )
99
+
100
+ def detokenize(self, inputs, *args, **kwargs):
101
+ """Transform tokens back into strings.
102
+
103
+ Args:
104
+ inputs: Input tensor, or dict/list/tuple of input tensors.
105
+ *args: Additional positional arguments.
106
+ **kwargs: Additional keyword arguments.
107
+ """
108
+ raise NotImplementedError(
109
+ "No implementation of `detokenize()` was found for "
110
+ f"{self.__class__.__name__}."
111
+ )
112
+
113
+ def get_vocabulary(self):
114
+ """Get the tokenizer vocabulary as a list of strings terms."""
115
+ raise NotImplementedError(
116
+ "No implementation of `get_vocabulary()` was found for "
117
+ f"{self.__class__.__name__}."
118
+ )
119
+
120
+ def vocabulary_size(self):
121
+ """Returns the total size of the token id space."""
122
+ raise NotImplementedError(
123
+ "No implementation of `vocabulary_size()` was found for "
124
+ f"{self.__class__.__name__}."
125
+ )
126
+
127
+ def id_to_token(self, id):
128
+ """Convert an integer id to a string token."""
129
+ raise NotImplementedError(
130
+ "No implementation of `id_to_token()` was found for "
131
+ f"{self.__class__.__name__}."
132
+ )
133
+
134
+ def token_to_id(self, token):
135
+ """Convert a string token to an integer id."""
136
+ raise NotImplementedError(
137
+ "No implementation of `token_to_id()` was found for "
138
+ f"{self.__class__.__name__}."
139
+ )
140
+
141
+ def save_to_preset(self, preset_dir):
142
+ """Save tokenizer to a preset directory.
143
+
144
+ Args:
145
+ preset_dir: The path to the local model preset directory.
146
+ """
147
+ save_serialized_object(
148
+ self,
149
+ preset_dir,
150
+ config_file=TOKENIZER_CONFIG_FILE,
151
+ )
152
+ save_tokenizer_assets(self, preset_dir)
153
+
154
+ def call(self, inputs, *args, training=None, **kwargs):
155
+ return self.tokenize(inputs, *args, **kwargs)
156
+
157
+ def load_preset_assets(self, preset):
158
+ asset_path = None
159
+ for asset in self.file_assets:
160
+ asset_path = get_file(
161
+ preset, os.path.join(TOKENIZER_ASSET_DIR, asset)
162
+ )
163
+ tokenizer_asset_dir = os.path.dirname(asset_path)
164
+ self.load_assets(tokenizer_asset_dir)
165
+
166
+ @classproperty
167
+ def presets(cls):
168
+ """List built-in presets for a `Task` subclass."""
169
+ presets = list_presets(cls)
170
+ for subclass in list_subclasses(cls):
171
+ presets.update(subclass.presets)
172
+ return presets
173
+
174
+ @classmethod
175
+ def from_preset(
176
+ cls,
177
+ preset,
178
+ **kwargs,
179
+ ):
180
+ """Instantiate a `keras_hub.models.Tokenizer` from a model preset.
181
+
182
+ A preset is a directory of configs, weights and other file assets used
183
+ to save and load a pre-trained model. The `preset` can be passed as a
184
+ one of:
185
+
186
+ 1. a built in preset identifier like `'bert_base_en'`
187
+ 2. a Kaggle Models handle like `'kaggle://user/bert/keras/bert_base_en'`
188
+ 3. a Hugging Face handle like `'hf://user/bert_base_en'`
189
+ 4. a path to a local preset directory like `'./bert_base_en'`
190
+
191
+ For any `Tokenizer` subclass, you can run `cls.presets.keys()` to list
192
+ all built-in presets available on the class.
193
+
194
+ This constructor can be called in one of two ways. Either from the base
195
+ class like `keras_hub.models.Tokenizer.from_preset()`, or from
196
+ a model class like `keras_hub.models.GemmaTokenizer.from_preset()`.
197
+ If calling from the base class, the subclass of the returning object
198
+ will be inferred from the config in the preset directory.
199
+
200
+ Args:
201
+ preset: string. A built in preset identifier, a Kaggle Models
202
+ handle, a Hugging Face handle, or a path to a local directory.
203
+ load_weights: bool. If `True`, the weights will be loaded into the
204
+ model architecture. If `False`, the weights will be randomly
205
+ initialized.
206
+
207
+ Examples:
208
+ ```python
209
+ # Load a preset tokenizer.
210
+ tokenizer = keras_hub.tokenizerTokenizer.from_preset("bert_base_en")
211
+
212
+ # Tokenize some input.
213
+ tokenizer("The quick brown fox tripped.")
214
+
215
+ # Detokenize some input.
216
+ tokenizer.detokenize([5, 6, 7, 8, 9])
217
+ ```
218
+ """
219
+ format = check_format(preset)
220
+ if format == "transformers":
221
+ return load_transformers_tokenizer(cls, preset)
222
+
223
+ preset_cls = check_config_class(
224
+ preset, config_file=TOKENIZER_CONFIG_FILE
225
+ )
226
+ if not issubclass(preset_cls, cls):
227
+ raise ValueError(
228
+ f"Preset has type `{preset_cls.__name__}` which is not a "
229
+ f"a subclass of calling class `{cls.__name__}`. Call "
230
+ f"`from_preset` directly on `{preset_cls.__name__}` instead."
231
+ )
232
+
233
+ tokenizer = load_serialized_object(preset, TOKENIZER_CONFIG_FILE)
234
+ tokenizer.load_preset_assets(preset)
235
+ return tokenizer