Added model and tokenizer
Browse files- config.json +126 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/Colab Notebooks/HF_Language_Detection/Models/bert-base-multilingual-cased-language-detection",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15",
|
29 |
+
"16": "LABEL_16",
|
30 |
+
"17": "LABEL_17",
|
31 |
+
"18": "LABEL_18",
|
32 |
+
"19": "LABEL_19",
|
33 |
+
"20": "LABEL_20",
|
34 |
+
"21": "LABEL_21",
|
35 |
+
"22": "LABEL_22",
|
36 |
+
"23": "LABEL_23",
|
37 |
+
"24": "LABEL_24",
|
38 |
+
"25": "LABEL_25",
|
39 |
+
"26": "LABEL_26",
|
40 |
+
"27": "LABEL_27",
|
41 |
+
"28": "LABEL_28",
|
42 |
+
"29": "LABEL_29",
|
43 |
+
"30": "LABEL_30",
|
44 |
+
"31": "LABEL_31",
|
45 |
+
"32": "LABEL_32",
|
46 |
+
"33": "LABEL_33",
|
47 |
+
"34": "LABEL_34",
|
48 |
+
"35": "LABEL_35",
|
49 |
+
"36": "LABEL_36",
|
50 |
+
"37": "LABEL_37",
|
51 |
+
"38": "LABEL_38",
|
52 |
+
"39": "LABEL_39",
|
53 |
+
"40": "LABEL_40",
|
54 |
+
"41": "LABEL_41",
|
55 |
+
"42": "LABEL_42",
|
56 |
+
"43": "LABEL_43",
|
57 |
+
"44": "LABEL_44"
|
58 |
+
},
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"label2id": {
|
62 |
+
"LABEL_0": 0,
|
63 |
+
"LABEL_1": 1,
|
64 |
+
"LABEL_10": 10,
|
65 |
+
"LABEL_11": 11,
|
66 |
+
"LABEL_12": 12,
|
67 |
+
"LABEL_13": 13,
|
68 |
+
"LABEL_14": 14,
|
69 |
+
"LABEL_15": 15,
|
70 |
+
"LABEL_16": 16,
|
71 |
+
"LABEL_17": 17,
|
72 |
+
"LABEL_18": 18,
|
73 |
+
"LABEL_19": 19,
|
74 |
+
"LABEL_2": 2,
|
75 |
+
"LABEL_20": 20,
|
76 |
+
"LABEL_21": 21,
|
77 |
+
"LABEL_22": 22,
|
78 |
+
"LABEL_23": 23,
|
79 |
+
"LABEL_24": 24,
|
80 |
+
"LABEL_25": 25,
|
81 |
+
"LABEL_26": 26,
|
82 |
+
"LABEL_27": 27,
|
83 |
+
"LABEL_28": 28,
|
84 |
+
"LABEL_29": 29,
|
85 |
+
"LABEL_3": 3,
|
86 |
+
"LABEL_30": 30,
|
87 |
+
"LABEL_31": 31,
|
88 |
+
"LABEL_32": 32,
|
89 |
+
"LABEL_33": 33,
|
90 |
+
"LABEL_34": 34,
|
91 |
+
"LABEL_35": 35,
|
92 |
+
"LABEL_36": 36,
|
93 |
+
"LABEL_37": 37,
|
94 |
+
"LABEL_38": 38,
|
95 |
+
"LABEL_39": 39,
|
96 |
+
"LABEL_4": 4,
|
97 |
+
"LABEL_40": 40,
|
98 |
+
"LABEL_41": 41,
|
99 |
+
"LABEL_42": 42,
|
100 |
+
"LABEL_43": 43,
|
101 |
+
"LABEL_44": 44,
|
102 |
+
"LABEL_5": 5,
|
103 |
+
"LABEL_6": 6,
|
104 |
+
"LABEL_7": 7,
|
105 |
+
"LABEL_8": 8,
|
106 |
+
"LABEL_9": 9
|
107 |
+
},
|
108 |
+
"layer_norm_eps": 1e-12,
|
109 |
+
"max_position_embeddings": 512,
|
110 |
+
"model_type": "bert",
|
111 |
+
"num_attention_heads": 12,
|
112 |
+
"num_hidden_layers": 12,
|
113 |
+
"pad_token_id": 0,
|
114 |
+
"pooler_fc_size": 768,
|
115 |
+
"pooler_num_attention_heads": 12,
|
116 |
+
"pooler_num_fc_layers": 3,
|
117 |
+
"pooler_size_per_head": 128,
|
118 |
+
"pooler_type": "first_token_transform",
|
119 |
+
"position_embedding_type": "absolute",
|
120 |
+
"problem_type": "single_label_classification",
|
121 |
+
"torch_dtype": "float32",
|
122 |
+
"transformers_version": "4.12.5",
|
123 |
+
"type_vocab_size": 2,
|
124 |
+
"use_cache": true,
|
125 |
+
"vocab_size": 119547
|
126 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d37b3d75938317c87f6fdb040fc63e22818d29ffa9c357d6ca5b36c2b6a4733
|
3 |
+
size 711633453
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/content/drive/MyDrive/Colab Notebooks/HF_Language_Detection/Tokenizer", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|