Commit
•
8ccb9f1
1
Parent(s):
951cde5
model
Browse files- config.json +122 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"finetuning_task": "ner",
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "B-AGE",
|
16 |
+
"1": "B-DATE",
|
17 |
+
"2": "B-EMAIL",
|
18 |
+
"3": "B-HOSP",
|
19 |
+
"4": "B-ID",
|
20 |
+
"5": "B-LOC",
|
21 |
+
"6": "B-OTHERPHI",
|
22 |
+
"7": "B-PATIENT",
|
23 |
+
"8": "B-PATORG",
|
24 |
+
"9": "B-PHONE",
|
25 |
+
"10": "B-STAFF",
|
26 |
+
"11": "I-AGE",
|
27 |
+
"12": "I-DATE",
|
28 |
+
"13": "I-EMAIL",
|
29 |
+
"14": "I-HOSP",
|
30 |
+
"15": "I-ID",
|
31 |
+
"16": "I-LOC",
|
32 |
+
"17": "I-OTHERPHI",
|
33 |
+
"18": "I-PATIENT",
|
34 |
+
"19": "I-PATORG",
|
35 |
+
"20": "I-PHONE",
|
36 |
+
"21": "I-STAFF",
|
37 |
+
"22": "L-AGE",
|
38 |
+
"23": "L-DATE",
|
39 |
+
"24": "L-EMAIL",
|
40 |
+
"25": "L-HOSP",
|
41 |
+
"26": "L-ID",
|
42 |
+
"27": "L-LOC",
|
43 |
+
"28": "L-OTHERPHI",
|
44 |
+
"29": "L-PATIENT",
|
45 |
+
"30": "L-PATORG",
|
46 |
+
"31": "L-PHONE",
|
47 |
+
"32": "L-STAFF",
|
48 |
+
"33": "O",
|
49 |
+
"34": "U-AGE",
|
50 |
+
"35": "U-DATE",
|
51 |
+
"36": "U-EMAIL",
|
52 |
+
"37": "U-HOSP",
|
53 |
+
"38": "U-ID",
|
54 |
+
"39": "U-LOC",
|
55 |
+
"40": "U-OTHERPHI",
|
56 |
+
"41": "U-PATIENT",
|
57 |
+
"42": "U-PATORG",
|
58 |
+
"43": "U-PHONE",
|
59 |
+
"44": "U-STAFF"
|
60 |
+
},
|
61 |
+
"initializer_range": 0.02,
|
62 |
+
"intermediate_size": 4096,
|
63 |
+
"label2id": {
|
64 |
+
"B-AGE": 0,
|
65 |
+
"B-DATE": 1,
|
66 |
+
"B-EMAIL": 2,
|
67 |
+
"B-HOSP": 3,
|
68 |
+
"B-ID": 4,
|
69 |
+
"B-LOC": 5,
|
70 |
+
"B-OTHERPHI": 6,
|
71 |
+
"B-PATIENT": 7,
|
72 |
+
"B-PATORG": 8,
|
73 |
+
"B-PHONE": 9,
|
74 |
+
"B-STAFF": 10,
|
75 |
+
"I-AGE": 11,
|
76 |
+
"I-DATE": 12,
|
77 |
+
"I-EMAIL": 13,
|
78 |
+
"I-HOSP": 14,
|
79 |
+
"I-ID": 15,
|
80 |
+
"I-LOC": 16,
|
81 |
+
"I-OTHERPHI": 17,
|
82 |
+
"I-PATIENT": 18,
|
83 |
+
"I-PATORG": 19,
|
84 |
+
"I-PHONE": 20,
|
85 |
+
"I-STAFF": 21,
|
86 |
+
"L-AGE": 22,
|
87 |
+
"L-DATE": 23,
|
88 |
+
"L-EMAIL": 24,
|
89 |
+
"L-HOSP": 25,
|
90 |
+
"L-ID": 26,
|
91 |
+
"L-LOC": 27,
|
92 |
+
"L-OTHERPHI": 28,
|
93 |
+
"L-PATIENT": 29,
|
94 |
+
"L-PATORG": 30,
|
95 |
+
"L-PHONE": 31,
|
96 |
+
"L-STAFF": 32,
|
97 |
+
"O": 33,
|
98 |
+
"U-AGE": 34,
|
99 |
+
"U-DATE": 35,
|
100 |
+
"U-EMAIL": 36,
|
101 |
+
"U-HOSP": 37,
|
102 |
+
"U-ID": 38,
|
103 |
+
"U-LOC": 39,
|
104 |
+
"U-OTHERPHI": 40,
|
105 |
+
"U-PATIENT": 41,
|
106 |
+
"U-PATORG": 42,
|
107 |
+
"U-PHONE": 43,
|
108 |
+
"U-STAFF": 44
|
109 |
+
},
|
110 |
+
"layer_norm_eps": 1e-05,
|
111 |
+
"max_position_embeddings": 514,
|
112 |
+
"model_type": "roberta",
|
113 |
+
"num_attention_heads": 16,
|
114 |
+
"num_hidden_layers": 24,
|
115 |
+
"pad_token_id": 1,
|
116 |
+
"position_embedding_type": "absolute",
|
117 |
+
"torch_dtype": "float32",
|
118 |
+
"transformers_version": "4.11.3",
|
119 |
+
"type_vocab_size": 1,
|
120 |
+
"use_cache": true,
|
121 |
+
"vocab_size": 50265
|
122 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e5e75ee896f33681a5acf6440d53831a110fd977c71d093260bb94e2a63bfa
|
3 |
+
size 1417588465
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|