felipovysk
commited on
Commit
•
8249fe5
1
Parent(s):
45ea1be
Upload tokenizer
Browse files- special_tokens_map.json +4 -10
- tokenizer.json +11 -6
- tokenizer_config.json +6 -7
special_tokens_map.json
CHANGED
@@ -2,28 +2,22 @@
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
5 |
-
"normalized":
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
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 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
26 |
-
"normalized":
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
}
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
+
"normalized": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
@@ -9,7 +14,7 @@
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized":
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
@@ -18,7 +23,7 @@
|
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
21 |
-
"normalized":
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
@@ -27,7 +32,7 @@
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
-
"normalized":
|
31 |
"special": true
|
32 |
},
|
33 |
{
|
@@ -36,8 +41,8 @@
|
|
36 |
"single_word": false,
|
37 |
"lstrip": false,
|
38 |
"rstrip": false,
|
39 |
-
"normalized":
|
40 |
-
"special":
|
41 |
}
|
42 |
],
|
43 |
"normalizer": {
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 128,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
14 |
"single_word": false,
|
15 |
"lstrip": false,
|
16 |
"rstrip": false,
|
17 |
+
"normalized": true,
|
18 |
"special": true
|
19 |
},
|
20 |
{
|
|
|
23 |
"single_word": false,
|
24 |
"lstrip": false,
|
25 |
"rstrip": false,
|
26 |
+
"normalized": true,
|
27 |
"special": true
|
28 |
},
|
29 |
{
|
|
|
32 |
"single_word": false,
|
33 |
"lstrip": false,
|
34 |
"rstrip": false,
|
35 |
+
"normalized": true,
|
36 |
"special": true
|
37 |
},
|
38 |
{
|
|
|
41 |
"single_word": false,
|
42 |
"lstrip": false,
|
43 |
"rstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"special": false
|
46 |
}
|
47 |
],
|
48 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -6,7 +6,7 @@
|
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
8 |
"lstrip": false,
|
9 |
-
"normalized":
|
10 |
"rstrip": false,
|
11 |
"single_word": false,
|
12 |
"special": true
|
@@ -14,7 +14,7 @@
|
|
14 |
"1": {
|
15 |
"content": "<s>",
|
16 |
"lstrip": false,
|
17 |
-
"normalized":
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
"special": true
|
@@ -22,7 +22,7 @@
|
|
22 |
"2": {
|
23 |
"content": "</s>",
|
24 |
"lstrip": false,
|
25 |
-
"normalized":
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
@@ -30,10 +30,10 @@
|
|
30 |
"32000": {
|
31 |
"content": "<pad>",
|
32 |
"lstrip": false,
|
33 |
-
"normalized":
|
34 |
"rstrip": false,
|
35 |
"single_word": false,
|
36 |
-
"special":
|
37 |
}
|
38 |
},
|
39 |
"bos_token": "<s>",
|
@@ -41,8 +41,7 @@
|
|
41 |
"eos_token": "</s>",
|
42 |
"legacy": false,
|
43 |
"model_max_length": 1000000000000000019884624838656,
|
44 |
-
"pad_token": "
|
45 |
-
"padding_side": "right",
|
46 |
"sp_model_kwargs": {},
|
47 |
"tokenizer_class": "LlamaTokenizer",
|
48 |
"unk_token": "<unk>",
|
|
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
8 |
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
"rstrip": false,
|
11 |
"single_word": false,
|
12 |
"special": true
|
|
|
14 |
"1": {
|
15 |
"content": "<s>",
|
16 |
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
"special": true
|
|
|
22 |
"2": {
|
23 |
"content": "</s>",
|
24 |
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
|
|
30 |
"32000": {
|
31 |
"content": "<pad>",
|
32 |
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
"rstrip": false,
|
35 |
"single_word": false,
|
36 |
+
"special": false
|
37 |
}
|
38 |
},
|
39 |
"bos_token": "<s>",
|
|
|
41 |
"eos_token": "</s>",
|
42 |
"legacy": false,
|
43 |
"model_max_length": 1000000000000000019884624838656,
|
44 |
+
"pad_token": "</s>",
|
|
|
45 |
"sp_model_kwargs": {},
|
46 |
"tokenizer_class": "LlamaTokenizer",
|
47 |
"unk_token": "<unk>",
|