Added models

README.md

@@ -0,0 +1,83 @@
+---
+language: ja
+tags:
+- t5
+- text2text-generation
+- seq2seq
+license: apache-2.0
+datasets:
+- mc4
+- wiki40b
+---
+
+# t5-base-japanese-web (with Byte-fallback, 8K)
+
+## Description
+
+[megagonlabs/t5-base-japanese-web](https://huggingface.co/megagonlabs/t5-base-japanese-web) is a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts.  
+Training codes are [available on GitHub](https://github.com/megagonlabs/t5-japanese).
+
+The vocabulary size of this model is 8K.
+[32K version is also available](https://huggingface.co/megagonlabs/t5-base-japanese-web).
+
+### Corpora
+
+We used following corpora for pre-training.
+
+- Japanese in [mC4/3.0.1](https://huggingface.co/datasets/mc4) (We used [Tensorflow native format](https://github.com/allenai/allennlp/discussions/5056))
+    - 87,425,304 pages
+    - 782 GB in TFRecord format
+- [Japanese](https://www.tensorflow.org/datasets/catalog/wiki40b#wiki40bja) in [wiki40b/1.3.0](https://www.tensorflow.org/datasets/catalog/wiki40b)
+    - 828,236 articles (2,073,584 examples)
+    - 2 GB in TFRecord format
+
+### Tokenizer
+
+We used Japanese Wikipedia to train [SentencePiece](https://github.com/google/sentencepiece).
+
+- Vocabulary size: 8,000
+- [Byte-fallback](https://github.com/google/sentencepiece/releases/tag/v0.1.9): Enabled
+
+### Parameters
+
+- T5 model: [models/t5.1.1.base.gin](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/t5/models/gin/models/t5.1.1.base.gin)
+- Training steps: 1,000,000
+
+It took about 126 hours with TPU v3-8
+
+## Related models
+
+- [日本語T5事前学習済みモデル (sonoisa/t5-base-japanese)](https://huggingface.co/sonoisa/t5-base-japanese)
+- [日本語T5事前学習済みモデル (sonoisa/t5-base-japanese-mC4-Wikipedia)](https://huggingface.co/sonoisa/t5-base-japanese-mC4-Wikipedia)
+
+## License
+
+Apache License 2.0
+
+## Citations
+
+- mC4
+
+Contains information from `mC4` which is made available under the [ODC Attribution License](https://opendatacommons.org/licenses/by/1-0/).
+
+```bibtex
+@article{2019t5,
+    author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
+    title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
+    journal = {arXiv e-prints},
+    year = {2019},
+    archivePrefix = {arXiv},
+    eprint = {1910.10683},
+}
+```
+
+- wiki40b
+
+```bibtex
+@inproceedings{49029,
+title = {Wiki-40B: Multilingual Language Model Dataset},
+author = {Mandy Guo and Zihang Dai and Denny Vrandecic and Rami Al-Rfou},
+year = {2020},
+booktitle   = {LREC 2020}
+}
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 8064
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb7e0cb580026b082401f28104f1e334aa97ec50ee72ab57b85238ec3c758b2
+size 842585165

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44349399ce87d5409b3ca15780d27ada474dc74ff2a112b08402605444e61a2a
+size 350029

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}