merge
Browse files- .gitattributes +1 -0
- config.json +44 -2
- tokenizer.json +0 -0
.gitattributes
CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
vocab.txt filter=lfs diff=lfs merge=lfs -text
|
|
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
vocab.txt filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -1,12 +1,22 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"BertForJointParsing"
|
4 |
],
|
|
|
5 |
"auto_map": {
|
6 |
"AutoModel": "dicta-il/dictabert-joint--BertForJointParsing.BertForJointParsing"
|
7 |
},
|
8 |
-
"attention_probs_dropout_prob": 0.1,
|
9 |
"classifier_dropout": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"do_lex": true,
|
11 |
"do_morph": true,
|
12 |
"do_ner": true,
|
@@ -83,9 +93,41 @@
|
|
83 |
"num_hidden_layers": 24,
|
84 |
"pad_token_id": 0,
|
85 |
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
"syntax_head_size": 128,
|
87 |
"torch_dtype": "float32",
|
88 |
-
"transformers_version": "4.
|
89 |
"type_vocab_size": 2,
|
90 |
"use_cache": true,
|
91 |
"vocab_size": 128000
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Hiveurban/dictabert-large-parse",
|
3 |
"architectures": [
|
4 |
"BertForJointParsing"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
"auto_map": {
|
8 |
"AutoModel": "dicta-il/dictabert-joint--BertForJointParsing.BertForJointParsing"
|
9 |
},
|
|
|
10 |
"classifier_dropout": null,
|
11 |
+
"custom_pipelines": {
|
12 |
+
"hive-token-classification": {
|
13 |
+
"impl": "hive_token_classification.HiveTokenClassification",
|
14 |
+
"pt": [
|
15 |
+
"AutoModel"
|
16 |
+
],
|
17 |
+
"tf": []
|
18 |
+
}
|
19 |
+
},
|
20 |
"do_lex": true,
|
21 |
"do_morph": true,
|
22 |
"do_ner": true,
|
|
|
93 |
"num_hidden_layers": 24,
|
94 |
"pad_token_id": 0,
|
95 |
"position_embedding_type": "absolute",
|
96 |
+
"prefix_cfg": {
|
97 |
+
"possible_classes": [
|
98 |
+
[
|
99 |
+
"\u05dc\u05db\u05e9",
|
100 |
+
"\u05db\u05e9",
|
101 |
+
"\u05de\u05e9",
|
102 |
+
"\u05d1\u05e9",
|
103 |
+
"\u05dc\u05e9"
|
104 |
+
],
|
105 |
+
[
|
106 |
+
"\u05de"
|
107 |
+
],
|
108 |
+
[
|
109 |
+
"\u05e9"
|
110 |
+
],
|
111 |
+
[
|
112 |
+
"\u05d4"
|
113 |
+
],
|
114 |
+
[
|
115 |
+
"\u05d5"
|
116 |
+
],
|
117 |
+
[
|
118 |
+
"\u05db"
|
119 |
+
],
|
120 |
+
[
|
121 |
+
"\u05dc"
|
122 |
+
],
|
123 |
+
[
|
124 |
+
"\u05d1"
|
125 |
+
]
|
126 |
+
]
|
127 |
+
},
|
128 |
"syntax_head_size": 128,
|
129 |
"torch_dtype": "float32",
|
130 |
+
"transformers_version": "4.44.2",
|
131 |
"type_vocab_size": 2,
|
132 |
"use_cache": true,
|
133 |
"vocab_size": 128000
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|