KoichiYasuoka commited on
Commit
befb284
1 Parent(s): f356dac

initial release

Browse files
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "ja"
4
+ tags:
5
+ - "japanese"
6
+ - "masked-lm"
7
+ - "wikipedia"
8
+ license: "cc-by-sa-4.0"
9
+ pipeline_tag: "fill-mask"
10
+ mask_token: "[MASK]"
11
+ widget:
12
+ - text: "日本に着いたら[MASK]を訪ねなさい。"
13
+ ---
14
+
15
+ # deberta-large-japanese-wikipedia
16
+
17
+ ## Model Description
18
+
19
+ This is a DeBERTa(V2) model pre-trained on Japanese Wikipedia and 青空文庫 texts. You can fine-tune `deberta-large-japanese-wikipedia` for downstream tasks, such as POS-tagging, dependency-parsing, and so on.
20
+
21
+ ## How to Use
22
+
23
+ ```py
24
+ from transformers import AutoTokenizer,AutoModelForMaskedLM
25
+ tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-large-japanese-wikipedia")
26
+ model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-large-japanese-wikipedia")
27
+ ```
28
+
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-07,
14
+ "max_position_embeddings": 512,
15
+ "max_relative_positions": -1,
16
+ "model_type": "deberta-v2",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 1,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": null,
24
+ "position_biased_input": true,
25
+ "relative_attention": false,
26
+ "tokenizer_class": "DebertaV2TokenizerFast",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.19.4",
29
+ "type_vocab_size": 0,
30
+ "vocab_size": 32000
31
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:395998a21d87799439f37b20396145f1592517cc2967bc5ba6e442217710e531
3
+ size 1346887533
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b
3
+ size 1
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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"}