initial release

README.md

@@ -0,0 +1,28 @@
+---
+language:
+- "ja"
+tags:
+- "japanese"
+- "masked-lm"
+- "wikipedia"
+license: "cc-by-sa-4.0"
+pipeline_tag: "fill-mask"
+mask_token: "[MASK]"
+widget:
+- text: "日本に着いたら[MASK]を訪ねなさい。"
+---
+
+# deberta-base-japanese-wikipedia
+
+## Model Description
+
+This is a DeBERTa(V2) model pre-trained on Japanese Wikipedia and 青空文庫 texts. You can fine-tune `deberta-base-japanese-wikipedia` for downstream tasks, such as POS-tagging, dependency-parsing, and so on.
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForMaskedLM
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-japanese-wikipedia")
+model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-base-japanese-wikipedia")
+```
+

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": null,
+  "position_biased_input": true,
+  "relative_attention": false,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.4",
+  "type_vocab_size": 0,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568fc41e8290860e79315639fe360d87248789706da888837d47812ec3c9eb8e
+size 442669613

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": "[MASK]"}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b
+size 1

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": true, "keep_accents": true, "model_max_length": 512, "tokenizer_class": "DebertaV2TokenizerFast"}