Added POS tagging model
Browse files- README.md +3 -0
- config.json +120 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
---
|
config.json
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "``",
|
14 |
+
"2": ",",
|
15 |
+
"3": ":",
|
16 |
+
"4": ".",
|
17 |
+
"5": "''",
|
18 |
+
"6": "$",
|
19 |
+
"7": "#",
|
20 |
+
"8": "CC",
|
21 |
+
"9": "CD",
|
22 |
+
"10": "DT",
|
23 |
+
"11": "EX",
|
24 |
+
"12": "FW",
|
25 |
+
"13": "IN",
|
26 |
+
"14": "JJ",
|
27 |
+
"15": "JJR",
|
28 |
+
"16": "JJS",
|
29 |
+
"17": "-LRB-",
|
30 |
+
"18": "LS",
|
31 |
+
"19": "MD",
|
32 |
+
"20": "NN",
|
33 |
+
"21": "NNP",
|
34 |
+
"22": "NNPS",
|
35 |
+
"23": "NNS",
|
36 |
+
"24": "PDT",
|
37 |
+
"25": "POS",
|
38 |
+
"26": "PRP",
|
39 |
+
"27": "PRP$",
|
40 |
+
"28": "RB",
|
41 |
+
"29": "RBR",
|
42 |
+
"30": "RBS",
|
43 |
+
"31": "RP",
|
44 |
+
"32": "-RRB-",
|
45 |
+
"33": "SYM",
|
46 |
+
"34": "TO",
|
47 |
+
"35": "UH",
|
48 |
+
"36": "VB",
|
49 |
+
"37": "VBD",
|
50 |
+
"38": "VBG",
|
51 |
+
"39": "VBN",
|
52 |
+
"40": "VBP",
|
53 |
+
"41": "VBZ",
|
54 |
+
"42": "WDT",
|
55 |
+
"43": "WP",
|
56 |
+
"44": "WP$",
|
57 |
+
"45": "WRB"
|
58 |
+
},
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"label2id": {
|
62 |
+
"#": 7,
|
63 |
+
"$": 6,
|
64 |
+
"''": 5,
|
65 |
+
",": 2,
|
66 |
+
"-LRB-": 17,
|
67 |
+
"-RRB-": 32,
|
68 |
+
".": 4,
|
69 |
+
":": 3,
|
70 |
+
"CC": 8,
|
71 |
+
"CD": 9,
|
72 |
+
"DT": 10,
|
73 |
+
"EX": 11,
|
74 |
+
"FW": 12,
|
75 |
+
"IN": 13,
|
76 |
+
"JJ": 14,
|
77 |
+
"JJR": 15,
|
78 |
+
"JJS": 16,
|
79 |
+
"LS": 18,
|
80 |
+
"MD": 19,
|
81 |
+
"NN": 20,
|
82 |
+
"NNP": 21,
|
83 |
+
"NNPS": 22,
|
84 |
+
"NNS": 23,
|
85 |
+
"O": 0,
|
86 |
+
"PDT": 24,
|
87 |
+
"POS": 25,
|
88 |
+
"PRP": 26,
|
89 |
+
"PRP$": 27,
|
90 |
+
"RB": 28,
|
91 |
+
"RBR": 29,
|
92 |
+
"RBS": 30,
|
93 |
+
"RP": 31,
|
94 |
+
"SYM": 33,
|
95 |
+
"TO": 34,
|
96 |
+
"UH": 35,
|
97 |
+
"VB": 36,
|
98 |
+
"VBD": 37,
|
99 |
+
"VBG": 38,
|
100 |
+
"VBN": 39,
|
101 |
+
"VBP": 40,
|
102 |
+
"VBZ": 41,
|
103 |
+
"WDT": 42,
|
104 |
+
"WP": 43,
|
105 |
+
"WP$": 44,
|
106 |
+
"WRB": 45,
|
107 |
+
"``": 1
|
108 |
+
},
|
109 |
+
"layer_norm_eps": 1e-12,
|
110 |
+
"max_position_embeddings": 512,
|
111 |
+
"model_type": "bert",
|
112 |
+
"num_attention_heads": 12,
|
113 |
+
"num_hidden_layers": 12,
|
114 |
+
"pad_token_id": 0,
|
115 |
+
"position_embedding_type": "absolute",
|
116 |
+
"transformers_version": "4.6.1",
|
117 |
+
"type_vocab_size": 2,
|
118 |
+
"use_cache": true,
|
119 |
+
"vocab_size": 28996
|
120 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b106eb70490e06706354f181926f8e49e1c57e0dd416e3bb48c0dbbf2e4b82fb
|
3 |
+
size 431108791
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "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, "tokenizer_file": "/home/local/QCRI/ndurrani/.cache/huggingface/transformers/226a307193a9f4344264cdc76a12988448a25345ba172f2c7421f3b6810fddad.3dab63143af66769bbb35e3811f75f7e16b2320e12b7935e216bd6159ce6d9a6", "name_or_path": "bert-base-cased"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c11885b5f3e0e62601f8e85237c40abf6dd794010b0ebf0e7dfabb623ed0c70
|
3 |
+
size 2415
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|