Hugging Face's logo

KoichiYasuoka
/
modernbert-base-japanese-aozora-upos

Token Classification
PyTorch
Japanese
modernbert
japanese
pos
custom_code
Model card Files Community
2
modernbert-base-japanese-aozora-upos
File size: 4,222 Bytes 
37eaef1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
{
  "architectures": [
    "ModernBertForTokenClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_modernbert.ModernBertConfig",
    "AutoModel": "modeling_modernbert.ModernBertModel",
    "AutoModelForMaskedLM": "modeling_modernbert.ModernBertForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_modernbert.ModernBertForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_modernbert.ModernBertForTokenClassification"
  },
  "bos_token_id": 0,
  "classifier_activation": "gelu",
  "classifier_bias": false,
  "classifier_dropout": 0.0,
  "classifier_pooling": "mean",
  "cls_token_id": 0,
  "custom_pipelines": {
    "upos": {
      "impl": "upos.BellmanFordTokenClassificationPipeline",
      "pt": "AutoModelForTokenClassification"
    }
  },
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "embedding_dropout": 0.0,
  "eos_token_id": 2,
  "global_attn_every_n_layers": 3,
  "global_rope_theta": 160000.0,
  "gradient_checkpointing": false,
  "hidden_activation": "gelu",
  "hidden_size": 768,
  "id2label": {
    "0": "ADJ",
    "1": "B-ADJ",
    "2": "I-ADJ",
    "3": "ADJ|Polarity=Neg",
    "4": "B-ADJ|Polarity=Neg",
    "5": "I-ADJ|Polarity=Neg",
    "6": "ADP",
    "7": "B-ADP",
    "8": "I-ADP",
    "9": "ADV",
    "10": "B-ADV",
    "11": "I-ADV",
    "12": "AUX",
    "13": "B-AUX",
    "14": "I-AUX",
    "15": "AUX|Polarity=Neg",
    "16": "B-AUX|Polarity=Neg",
    "17": "I-AUX|Polarity=Neg",
    "18": "CCONJ",
    "19": "B-CCONJ",
    "20": "I-CCONJ",
    "21": "DET",
    "22": "B-DET",
    "23": "I-DET",
    "24": "INTJ",
    "25": "B-INTJ",
    "26": "I-INTJ",
    "27": "NOUN",
    "28": "B-NOUN",
    "29": "I-NOUN",
    "30": "NOUN|Polarity=Neg",
    "31": "B-NOUN|Polarity=Neg",
    "32": "I-NOUN|Polarity=Neg",
    "33": "NUM",
    "34": "B-NUM",
    "35": "I-NUM",
    "36": "PART",
    "37": "B-PART",
    "38": "I-PART",
    "39": "PRON",
    "40": "B-PRON",
    "41": "I-PRON",
    "42": "PROPN",
    "43": "B-PROPN",
    "44": "I-PROPN",
    "45": "PUNCT",
    "46": "B-PUNCT",
    "47": "I-PUNCT",
    "48": "SCONJ",
    "49": "B-SCONJ",
    "50": "I-SCONJ",
    "51": "SYM",
    "52": "B-SYM",
    "53": "I-SYM",
    "54": "VERB",
    "55": "B-VERB",
    "56": "I-VERB",
    "57": "X",
    "58": "B-X",
    "59": "I-X"
  },
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 1152,
  "label2id": {
    "ADJ": 0,
    "ADJ|Polarity=Neg": 3,
    "ADP": 6,
    "ADV": 9,
    "AUX": 12,
    "AUX|Polarity=Neg": 15,
    "B-ADJ": 1,
    "B-ADJ|Polarity=Neg": 4,
    "B-ADP": 7,
    "B-ADV": 10,
    "B-AUX": 13,
    "B-AUX|Polarity=Neg": 16,
    "B-CCONJ": 19,
    "B-DET": 22,
    "B-INTJ": 25,
    "B-NOUN": 28,
    "B-NOUN|Polarity=Neg": 31,
    "B-NUM": 34,
    "B-PART": 37,
    "B-PRON": 40,
    "B-PROPN": 43,
    "B-PUNCT": 46,
    "B-SCONJ": 49,
    "B-SYM": 52,
    "B-VERB": 55,
    "B-X": 58,
    "CCONJ": 18,
    "DET": 21,
    "I-ADJ": 2,
    "I-ADJ|Polarity=Neg": 5,
    "I-ADP": 8,
    "I-ADV": 11,
    "I-AUX": 14,
    "I-AUX|Polarity=Neg": 17,
    "I-CCONJ": 20,
    "I-DET": 23,
    "I-INTJ": 26,
    "I-NOUN": 29,
    "I-NOUN|Polarity=Neg": 32,
    "I-NUM": 35,
    "I-PART": 38,
    "I-PRON": 41,
    "I-PROPN": 44,
    "I-PUNCT": 47,
    "I-SCONJ": 50,
    "I-SYM": 53,
    "I-VERB": 56,
    "I-X": 59,
    "INTJ": 24,
    "NOUN": 27,
    "NOUN|Polarity=Neg": 30,
    "NUM": 33,
    "PART": 36,
    "PRON": 39,
    "PROPN": 42,
    "PUNCT": 45,
    "SCONJ": 48,
    "SYM": 51,
    "VERB": 54,
    "X": 57
  },
  "layer_norm_eps": 1e-05,
  "local_attention": 128,
  "local_rope_theta": 10000.0,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "model_type": "modernbert",
  "norm_bias": false,
  "norm_eps": 1e-05,
  "num_attention_heads": 12,
  "num_hidden_layers": 22,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "reference_compile": true,
  "sep_token_id": 2,
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "tokenizer_class": "DebertaV2TokenizerFast",
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "vocab_size": 65000
}