KoichiYasuoka commited on
Commit
88feb34
1 Parent(s): e6917ab

model improved

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ widget:
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-base-japanese-wikipedia` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos), [dependency-parsing](https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-ud-head), and so on.
20
 
21
  ## How to Use
22
 
 
16
 
17
  ## Model Description
18
 
19
+ This is a DeBERTa(V2) model pre-trained on Japanese Wikipedia and 青空文庫 texts. NVIDIA A100-SXM4-40GB took 109 hours 27 minutes for training. You can fine-tune `deberta-base-japanese-wikipedia` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos), [dependency-parsing](https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-ud-head), and so on.
20
 
21
  ## How to Use
22
 
config.json CHANGED
@@ -20,12 +20,15 @@
20
  "pooler_dropout": 0,
21
  "pooler_hidden_act": "gelu",
22
  "pooler_hidden_size": 768,
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
  }
 
20
  "pooler_dropout": 0,
21
  "pooler_hidden_act": "gelu",
22
  "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "relative_attention": true,
29
  "tokenizer_class": "DebertaV2TokenizerFast",
30
  "torch_dtype": "float32",
31
+ "transformers_version": "4.22.1",
32
  "type_vocab_size": 0,
33
  "vocab_size": 32000
34
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:568fc41e8290860e79315639fe360d87248789706da888837d47812ec3c9eb8e
3
- size 442669613
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e611037011d102b0e3acf4d007577c4778c528b15370df9db684ad3cd24950
3
+ size 500956109
special_tokens_map.json CHANGED
@@ -1 +1,9 @@
1
- {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer_config.json CHANGED
@@ -1 +1,14 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "keep_accents": true,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "split_by_punct": true,
12
+ "tokenizer_class": "DebertaV2TokenizerFast",
13
+ "unk_token": "[UNK]"
14
+ }