Upload tokenizer
Browse files- special_tokens_map.json +6 -6
- tokenizer_config.json +6 -14
special_tokens_map.json
CHANGED
@@ -1,23 +1,23 @@
|
|
1 |
{
|
2 |
"eos_token": {
|
3 |
"content": "</s>",
|
4 |
-
"lstrip":
|
5 |
"normalized": false,
|
6 |
-
"rstrip":
|
7 |
"single_word": false
|
8 |
},
|
9 |
"pad_token": {
|
10 |
"content": "<pad>",
|
11 |
-
"lstrip":
|
12 |
"normalized": false,
|
13 |
-
"rstrip":
|
14 |
"single_word": false
|
15 |
},
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
-
"lstrip":
|
19 |
"normalized": false,
|
20 |
-
"rstrip":
|
21 |
"single_word": false
|
22 |
}
|
23 |
}
|
|
|
1 |
{
|
2 |
"eos_token": {
|
3 |
"content": "</s>",
|
4 |
+
"lstrip": true,
|
5 |
"normalized": false,
|
6 |
+
"rstrip": true,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"pad_token": {
|
10 |
"content": "<pad>",
|
11 |
+
"lstrip": true,
|
12 |
"normalized": false,
|
13 |
+
"rstrip": true,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
+
"lstrip": true,
|
19 |
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
"single_word": false
|
22 |
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -3,35 +3,27 @@
|
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": "<pad>",
|
6 |
-
"lstrip":
|
7 |
"normalized": false,
|
8 |
-
"rstrip":
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
"content": "</s>",
|
14 |
-
"lstrip":
|
15 |
"normalized": false,
|
16 |
-
"rstrip":
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
"content": "<unk>",
|
22 |
-
"lstrip":
|
23 |
"normalized": false,
|
24 |
-
"rstrip":
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
-
},
|
28 |
-
"250100": {
|
29 |
-
"content": "<hl>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": false
|
35 |
}
|
36 |
},
|
37 |
"additional_special_tokens": [],
|
|
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": "<pad>",
|
6 |
+
"lstrip": true,
|
7 |
"normalized": false,
|
8 |
+
"rstrip": true,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
"content": "</s>",
|
14 |
+
"lstrip": true,
|
15 |
"normalized": false,
|
16 |
+
"rstrip": true,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
"content": "<unk>",
|
22 |
+
"lstrip": true,
|
23 |
"normalized": false,
|
24 |
+
"rstrip": true,
|
25 |
"single_word": false,
|
26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
}
|
28 |
},
|
29 |
"additional_special_tokens": [],
|