Keep diff small
Browse files- config.json +2 -4
- special_tokens_map.json +1 -37
- tokenizer.json +0 -0
- tokenizer_config.json +1 -64
config.json
CHANGED
@@ -1,11 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"export_model_type": "transformer",
|
9 |
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
@@ -19,7 +17,7 @@
|
|
19 |
"num_hidden_layers": 6,
|
20 |
"pad_token_id": 0,
|
21 |
"position_embedding_type": "absolute",
|
22 |
-
"transformers_version": "4.
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
|
7 |
"gradient_checkpointing": false,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
|
|
17 |
"num_hidden_layers": 6,
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
+
"transformers_version": "4.8.2",
|
21 |
"type_vocab_size": 2,
|
22 |
"use_cache": true,
|
23 |
"vocab_size": 30522
|
special_tokens_map.json
CHANGED
@@ -1,37 +1 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": {
|
3 |
-
"content": "[CLS]",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
-
}
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,64 +1 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "[PAD]",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"100": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
-
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "[CLS]",
|
46 |
-
"do_basic_tokenize": true,
|
47 |
-
"do_lower_case": true,
|
48 |
-
"mask_token": "[MASK]",
|
49 |
-
"max_length": 128,
|
50 |
-
"model_max_length": 512,
|
51 |
-
"never_split": null,
|
52 |
-
"pad_to_multiple_of": null,
|
53 |
-
"pad_token": "[PAD]",
|
54 |
-
"pad_token_type_id": 0,
|
55 |
-
"padding_side": "right",
|
56 |
-
"sep_token": "[SEP]",
|
57 |
-
"stride": 0,
|
58 |
-
"strip_accents": null,
|
59 |
-
"tokenize_chinese_chars": true,
|
60 |
-
"tokenizer_class": "BertTokenizer",
|
61 |
-
"truncation_side": "right",
|
62 |
-
"truncation_strategy": "longest_first",
|
63 |
-
"unk_token": "[UNK]"
|
64 |
-
}
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "nreimers/MiniLM-L6-H384-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer", "model_max_length": 512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|