creat89
commited on
Commit
•
3bf46bc
0
Parent(s):
Upload model
Browse files- .gitattributes +27 -0
- README.md +3 -0
- config.json +124 -0
- mapping.pkl +0 -0
- params-2021latin_da-IOBES-S____EC__.txt +33 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
---
|
config.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BERT_model_multidata"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"finetuning_task": "2021latin_da-IOBES-S____EC__",
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8",
|
21 |
+
"9": "LABEL_9",
|
22 |
+
"10": "LABEL_10",
|
23 |
+
"11": "LABEL_11",
|
24 |
+
"12": "LABEL_12",
|
25 |
+
"13": "LABEL_13",
|
26 |
+
"14": "LABEL_14",
|
27 |
+
"15": "LABEL_15",
|
28 |
+
"16": "LABEL_16",
|
29 |
+
"17": "LABEL_17",
|
30 |
+
"18": "LABEL_18",
|
31 |
+
"19": "LABEL_19",
|
32 |
+
"20": "LABEL_20",
|
33 |
+
"21": "LABEL_21",
|
34 |
+
"22": "LABEL_22",
|
35 |
+
"23": "LABEL_23",
|
36 |
+
"24": "LABEL_24",
|
37 |
+
"25": "LABEL_25",
|
38 |
+
"26": "LABEL_26",
|
39 |
+
"27": "LABEL_27",
|
40 |
+
"28": "LABEL_28",
|
41 |
+
"29": "LABEL_29",
|
42 |
+
"30": "LABEL_30",
|
43 |
+
"31": "LABEL_31",
|
44 |
+
"32": "LABEL_32",
|
45 |
+
"33": "LABEL_33",
|
46 |
+
"34": "LABEL_34",
|
47 |
+
"35": "LABEL_35",
|
48 |
+
"36": "LABEL_36",
|
49 |
+
"37": "LABEL_37",
|
50 |
+
"38": "LABEL_38",
|
51 |
+
"39": "LABEL_39",
|
52 |
+
"40": "LABEL_40",
|
53 |
+
"41": "LABEL_41",
|
54 |
+
"42": "LABEL_42",
|
55 |
+
"43": "LABEL_43"
|
56 |
+
},
|
57 |
+
"initializer_range": 0.02,
|
58 |
+
"intermediate_size": 3072,
|
59 |
+
"label2id": {
|
60 |
+
"B-ART": 28,
|
61 |
+
"B-DATE": 40,
|
62 |
+
"B-EVT": 20,
|
63 |
+
"B-LOC": 12,
|
64 |
+
"B-MEDIA": 36,
|
65 |
+
"B-MISC": 24,
|
66 |
+
"B-ORG": 8,
|
67 |
+
"B-PER": 4,
|
68 |
+
"B-PRO": 16,
|
69 |
+
"B-TIME": 32,
|
70 |
+
"E-ART": 30,
|
71 |
+
"E-DATE": 42,
|
72 |
+
"E-EVT": 22,
|
73 |
+
"E-LOC": 14,
|
74 |
+
"E-MEDIA": 38,
|
75 |
+
"E-MISC": 26,
|
76 |
+
"E-ORG": 10,
|
77 |
+
"E-PER": 6,
|
78 |
+
"E-PRO": 18,
|
79 |
+
"E-TIME": 34,
|
80 |
+
"I-ART": 29,
|
81 |
+
"I-DATE": 41,
|
82 |
+
"I-EVT": 21,
|
83 |
+
"I-LOC": 13,
|
84 |
+
"I-MEDIA": 37,
|
85 |
+
"I-MISC": 25,
|
86 |
+
"I-ORG": 9,
|
87 |
+
"I-PER": 5,
|
88 |
+
"I-PRO": 17,
|
89 |
+
"I-TIME": 33,
|
90 |
+
"O": 1,
|
91 |
+
"S-ART": 31,
|
92 |
+
"S-DATE": 43,
|
93 |
+
"S-EVT": 23,
|
94 |
+
"S-LOC": 15,
|
95 |
+
"S-MEDIA": 39,
|
96 |
+
"S-MISC": 27,
|
97 |
+
"S-ORG": 11,
|
98 |
+
"S-PER": 7,
|
99 |
+
"S-PRO": 19,
|
100 |
+
"S-TIME": 35,
|
101 |
+
"[CLS]": 2,
|
102 |
+
"[SEP]": 3
|
103 |
+
},
|
104 |
+
"layer_norm_eps": 1e-12,
|
105 |
+
"max_position_embeddings": 512,
|
106 |
+
"model_type": "bert",
|
107 |
+
"num_attention_heads": 12,
|
108 |
+
"num_hidden_layers": 12,
|
109 |
+
"pad_token_id": 0,
|
110 |
+
"position_embedding_type": "absolute",
|
111 |
+
"task_specific_params": {
|
112 |
+
"bert_hidden_size": 768,
|
113 |
+
"biaffine": false,
|
114 |
+
"boundaries_labels": null,
|
115 |
+
"crf": true,
|
116 |
+
"md_model": true,
|
117 |
+
"md_number": 7,
|
118 |
+
"predict_boundaries": false,
|
119 |
+
"predict_masked": false,
|
120 |
+
"type_crf_constraints": "BIOES"
|
121 |
+
},
|
122 |
+
"type_vocab_size": 2,
|
123 |
+
"vocab_size": 501154
|
124 |
+
}
|
mapping.pkl
ADDED
Binary file (1.07 kB). View file
|
|
params-2021latin_da-IOBES-S____EC__.txt
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
seed: 12
|
2 |
+
file_extension: txt
|
3 |
+
experiment_name: 2021latin_da-IOBES-S____EC__
|
4 |
+
tags2use: NER_IOBES
|
5 |
+
special_labesl: True
|
6 |
+
force_size: False
|
7 |
+
train_file: train_*
|
8 |
+
masking_percentage: 0.0
|
9 |
+
seed: 12
|
10 |
+
epochs: 20
|
11 |
+
early_stop: 2
|
12 |
+
separator:
|
13 |
+
test_file: test
|
14 |
+
dev_file: dev_*
|
15 |
+
crf: True
|
16 |
+
uppercase: False
|
17 |
+
lr: 2e-05
|
18 |
+
epsilon: 1e-08
|
19 |
+
bert_model: /home/lcabrera/BERT_Models/LaBSE
|
20 |
+
mask_entities: False
|
21 |
+
train_batch_size: 5
|
22 |
+
comment_line: -DOCSTART
|
23 |
+
sequence_size: 128
|
24 |
+
multi_gpu: False
|
25 |
+
fullwords_mask: None
|
26 |
+
redundant_uppercase: None
|
27 |
+
bert_hidden_size: 768
|
28 |
+
no_dev: False
|
29 |
+
multidata_model: Daume
|
30 |
+
training_datasets: ['train_0_wikiann_CsPlSL', 'train_1_final_csplsl', 'train_2_bsnlp17_CsPlSL', 'train_3_ssj', 'train_4_kpwr2', 'train_5_cnec', 'train_6_turku']
|
31 |
+
predict_boundaries: False
|
32 |
+
biaffine: False
|
33 |
+
uppercase_percentahe: 0.0
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99d6b5a1c36b0f5770bb0b39a642a85959a08b7b1a0ac9546815dc8496bf1f00
|
3 |
+
size 1897145842
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|