Initial release.

README.md

@@ -0,0 +1,55 @@
+---
+language: ja
+license: cc-by-sa-4.0
+datasets:
+- wikipedia
+- cc100
+mask_token: "[MASK]"
+widget:
+- text: "早稲田 大学 で 自然 言語 処理 を [MASK] する 。"
+---
+
+# nlp-waseda/roberta-large-japanese
+
+## Model description
+
+This is a Japanese RoBERTa large model pretrained on Japanese Wikipedia and the Japanese portion of CC-100 with the maximum sequence length of 512.
+
+## How to use
+
+You can use this model for masked language modeling as follows:
+```python
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+tokenizer = AutoTokenizer.from_pretrained("nlp-waseda/roberta-large-japanese")
+model = AutoModelForMaskedLM.from_pretrained("nlp-waseda/roberta-large-japanese")
+
+sentence = '早稲田 大学 で 自然 言語 処理 を [MASK] する 。' # input should be segmented into words by Juman++ in advance
+encoding = tokenizer(sentence, return_tensors='pt')
+...
+```
+
+You can fine-tune this model on downstream tasks.
+
+## Tokenization
+
+The input text should be segmented into words by [Juman++](https://github.com/ku-nlp/jumanpp) in advance. Juman++ 2.0.0-rc3 was used for pretraining. Each word is tokenized into tokens by [sentencepiece](https://github.com/google/sentencepiece).
+
+## Vocabulary
+
+The vocabulary consists of 32000 tokens including words ([JumanDIC](https://github.com/ku-nlp/JumanDIC)) and subwords induced by the unigram language model of [sentencepiece](https://github.com/google/sentencepiece).
+
+## Training procedure
+
+This model was trained on Japanese Wikipedia (as of 20210920) and the Japanese portion of CC-100 from the checkpoint of [nlp-waseda/roberta-large-japanese](https://huggingface.co/nlp-waseda/roberta-large-japanese). It took a week using eight NVIDIA A100 GPUs.
+
+The following hyperparameters were used during pretraining:
+- learning_rate: 6e-5
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 4120 (max_seq_length=128), 4032 (max_seq_length=512)
+- max_seq_length: 512
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-6
+- lr_scheduler_type: linear
+- training_steps: 670000 (max_seq_length=128) + 70000 (max_seq_length=512)
+- warmup_steps: 10000
+- mixed_precision_training: Native AMP

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f4bafed9d4cc7e44d0f0714db18f9396e8410e842927b8305b05aee0cfdfeb
+size 1346903275

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f87f538d8c73fb0a6a34efb7ba6e3488f920341119c02c208bce7965cf248e
+size 810161

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_class": "AlbertTokenizer"}