shirayu commited on
Commit
9b69d11
1 Parent(s): 951eeb4

Added models

Browse files

README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ja
3
+ tags:
4
+ - t5
5
+ - text2text-generation
6
+ - seq2seq
7
+ license: apache-2.0
8
+ datasets:
9
+ - mc4
10
+ - wiki40b
11
+ ---
12
+
13
+ # t5-base-japanese-web (with Byte-fallback, 8K)
14
+
15
+ ## Description
16
+
17
+ [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.
18
+ Training codes are [available on GitHub](https://github.com/megagonlabs/t5-japanese).
19
+
20
+ The vocabulary size of this model is 8K.
21
+ [32K version is also available](https://huggingface.co/megagonlabs/t5-base-japanese-web).
22
+
23
+ ### Corpora
24
+
25
+ We used following corpora for pre-training.
26
+
27
+ - Japanese in [mC4/3.0.1](https://huggingface.co/datasets/mc4) (We used [Tensorflow native format](https://github.com/allenai/allennlp/discussions/5056))
28
+ - 87,425,304 pages
29
+ - 782 GB in TFRecord format
30
+ - [Japanese](https://www.tensorflow.org/datasets/catalog/wiki40b#wiki40bja) in [wiki40b/1.3.0](https://www.tensorflow.org/datasets/catalog/wiki40b)
31
+ - 828,236 articles (2,073,584 examples)
32
+ - 2 GB in TFRecord format
33
+
34
+ ### Tokenizer
35
+
36
+ We used Japanese Wikipedia to train [SentencePiece](https://github.com/google/sentencepiece).
37
+
38
+ - Vocabulary size: 8,000
39
+ - [Byte-fallback](https://github.com/google/sentencepiece/releases/tag/v0.1.9): Enabled
40
+
41
+ ### Parameters
42
+
43
+ - 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)
44
+ - Training steps: 1,000,000
45
+
46
+ It took about 126 hours with TPU v3-8
47
+
48
+ ## Related models
49
+
50
+ - [日本語T5事前学習済みモデル (sonoisa/t5-base-japanese)](https://huggingface.co/sonoisa/t5-base-japanese)
51
+ - [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)
52
+
53
+ ## License
54
+
55
+ Apache License 2.0
56
+
57
+ ## Citations
58
+
59
+ - mC4
60
+
61
+ Contains information from `mC4` which is made available under the [ODC Attribution License](https://opendatacommons.org/licenses/by/1-0/).
62
+
63
+ ```bibtex
64
+ @article{2019t5,
65
+ 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},
66
+ title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
67
+ journal = {arXiv e-prints},
68
+ year = {2019},
69
+ archivePrefix = {arXiv},
70
+ eprint = {1910.10683},
71
+ }
72
+ ```
73
+
74
+ - wiki40b
75
+
76
+ ```bibtex
77
+ @inproceedings{49029,
78
+ title = {Wiki-40B: Multilingual Language Model Dataset},
79
+ author = {Mandy Guo and Zihang Dai and Denny Vrandecic and Rami Al-Rfou},
80
+ year = {2020},
81
+ booktitle = {LREC 2020}
82
+ }
83
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "d_ff": 2048,
6
+ "d_kv": 64,
7
+ "d_model": 768,
8
+ "decoder_start_token_id": 0,
9
+ "dropout_rate": 0.1,
10
+ "eos_token_id": 1,
11
+ "feed_forward_proj": "gated-gelu",
12
+ "gradient_checkpointing": false,
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "transformers_version": "4.8.2",
25
+ "use_cache": true,
26
+ "vocab_size": 8064
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb7e0cb580026b082401f28104f1e334aa97ec50ee72ab57b85238ec3c758b2
3
+ size 842585165
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44349399ce87d5409b3ca15780d27ada474dc74ff2a112b08402605444e61a2a
3
+ size 350029
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
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"}