Upload tokenizer
Browse files- special_tokens_map.json +0 -28
- spiece.model +3 -0
- tokenizer_config.json +8 -31
special_tokens_map.json
CHANGED
@@ -1,18 +1,4 @@
|
|
1 |
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "<s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"eos_token": {
|
17 |
"content": "</s>",
|
18 |
"lstrip": false,
|
@@ -20,13 +6,6 @@
|
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "<mask>",
|
25 |
-
"lstrip": true,
|
26 |
-
"normalized": true,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
"pad_token": {
|
31 |
"content": "<pad>",
|
32 |
"lstrip": false,
|
@@ -34,13 +13,6 @@
|
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "</s>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
"unk_token": {
|
45 |
"content": "<unk>",
|
46 |
"lstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"eos_token": {
|
3 |
"content": "</s>",
|
4 |
"lstrip": false,
|
|
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
"pad_token": {
|
10 |
"content": "<pad>",
|
11 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,7 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
"content": "<pad>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,7 +9,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,39 +17,23 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
-
},
|
35 |
-
"46165": {
|
36 |
-
"content": "<mask>",
|
37 |
-
"lstrip": true,
|
38 |
-
"normalized": true,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
-
"cls_token": "<s>",
|
47 |
"eos_token": "</s>",
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"model_max_length":
|
51 |
-
"pad_to_multiple_of": null,
|
52 |
"pad_token": "<pad>",
|
53 |
-
"pad_token_type_id": 0,
|
54 |
-
"padding_side": "right",
|
55 |
-
"sep_token": "</s>",
|
56 |
"sp_model_kwargs": {},
|
57 |
-
"
|
58 |
-
"tokenizer_class": "XLMRobertaTokenizer",
|
59 |
-
"truncation_side": "right",
|
60 |
-
"truncation_strategy": "longest_first",
|
61 |
"unk_token": "<unk>"
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"content": "<pad>",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
|
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"1": {
|
13 |
"content": "</s>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
|
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
"content": "<unk>",
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
}
|
28 |
},
|
29 |
+
"additional_special_tokens": [],
|
30 |
"clean_up_tokenization_spaces": true,
|
|
|
31 |
"eos_token": "</s>",
|
32 |
+
"extra_ids": 0,
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
35 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
36 |
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
|
|
38 |
"unk_token": "<unk>"
|
39 |
}
|