Commit
•
03b6812
1
Parent(s):
d87ac20
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +33 -20
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
CHANGED
@@ -1,36 +1,44 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "O",
|
14 |
-
"1": "B-
|
15 |
-
"2": "I-
|
16 |
-
"3": "B-
|
17 |
-
"4": "I-
|
18 |
-
"5": "B-
|
19 |
-
"6": "I-
|
20 |
-
"7": "B-
|
21 |
-
"8": "I-
|
|
|
|
|
|
|
|
|
22 |
},
|
23 |
"initializer_range": 0.02,
|
24 |
"intermediate_size": 3072,
|
25 |
"label2id": {
|
26 |
-
"B-
|
27 |
-
"B-
|
28 |
-
"B-
|
29 |
-
"B-
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"I-
|
33 |
-
"I-
|
|
|
|
|
|
|
|
|
34 |
"O": 0
|
35 |
},
|
36 |
"layer_norm_eps": 1e-12,
|
@@ -39,10 +47,15 @@
|
|
39 |
"num_attention_heads": 12,
|
40 |
"num_hidden_layers": 12,
|
41 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
42 |
"position_embedding_type": "absolute",
|
43 |
"torch_dtype": "float32",
|
44 |
-
"transformers_version": "4.
|
45 |
"type_vocab_size": 2,
|
46 |
"use_cache": true,
|
47 |
-
"vocab_size":
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Babelscape/wikineural-multilingual-ner",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
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": "O",
|
14 |
+
"1": "B-corporation",
|
15 |
+
"2": "I-corporation",
|
16 |
+
"3": "B-creative-work",
|
17 |
+
"4": "I-creative-work",
|
18 |
+
"5": "B-group",
|
19 |
+
"6": "I-group",
|
20 |
+
"7": "B-location",
|
21 |
+
"8": "I-location",
|
22 |
+
"9": "B-person",
|
23 |
+
"10": "I-person",
|
24 |
+
"11": "B-product",
|
25 |
+
"12": "I-product"
|
26 |
},
|
27 |
"initializer_range": 0.02,
|
28 |
"intermediate_size": 3072,
|
29 |
"label2id": {
|
30 |
+
"B-corporation": 1,
|
31 |
+
"B-creative-work": 3,
|
32 |
+
"B-group": 5,
|
33 |
+
"B-location": 7,
|
34 |
+
"B-person": 9,
|
35 |
+
"B-product": 11,
|
36 |
+
"I-corporation": 2,
|
37 |
+
"I-creative-work": 4,
|
38 |
+
"I-group": 6,
|
39 |
+
"I-location": 8,
|
40 |
+
"I-person": 10,
|
41 |
+
"I-product": 12,
|
42 |
"O": 0
|
43 |
},
|
44 |
"layer_norm_eps": 1e-12,
|
|
|
47 |
"num_attention_heads": 12,
|
48 |
"num_hidden_layers": 12,
|
49 |
"pad_token_id": 0,
|
50 |
+
"pooler_fc_size": 768,
|
51 |
+
"pooler_num_attention_heads": 12,
|
52 |
+
"pooler_num_fc_layers": 3,
|
53 |
+
"pooler_size_per_head": 128,
|
54 |
+
"pooler_type": "first_token_transform",
|
55 |
"position_embedding_type": "absolute",
|
56 |
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.27.0.dev0",
|
58 |
"type_vocab_size": 2,
|
59 |
"use_cache": true,
|
60 |
+
"vocab_size": 119547
|
61 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19b092115eead75b466456ab33bf2e06bc8d1b12aacf6928b3fd20579df1a504
|
3 |
+
size 709160685
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
|
|
9 |
"strip_accents": null,
|
10 |
"tokenize_chinese_chars": true,
|
11 |
"tokenizer_class": "BertTokenizer",
|
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_lower_case": false,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
"pad_token": "[PAD]",
|
7 |
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
"strip_accents": null,
|
10 |
"tokenize_chinese_chars": true,
|
11 |
"tokenizer_class": "BertTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afdbe76b5cbf22e6a19c916ddd7f9ff30097725200d9a98a946f90d5770f3727
|
3 |
+
size 3515
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|