Upload tokenizer
Browse files- added_tokens.json +1 -2
- special_tokens_map.json +2 -2
- tokenizer.json +4 -4
- tokenizer_config.json +6 -6
added_tokens.json
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"1": 2
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"1 ": 1
|
|
|
3 |
}
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"bos_token": "0",
|
3 |
-
"eos_token": "1"
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "0 ",
|
3 |
+
"eos_token": "1 "
|
4 |
}
|
tokenizer.json
CHANGED
@@ -4,8 +4,8 @@
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
-
"id":
|
8 |
-
"content": "0",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
@@ -13,8 +13,8 @@
|
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
16 |
-
"id":
|
17 |
-
"content": "1",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "0 ",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
|
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "1 ",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
-
"content": "0",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
-
"content": "1",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
@@ -18,9 +18,9 @@
|
|
18 |
"special": true
|
19 |
}
|
20 |
},
|
21 |
-
"bos_token": "0",
|
22 |
"clean_up_tokenization_spaces": false,
|
23 |
-
"eos_token": "1",
|
24 |
"model_max_length": 1000000000000000019884624838656,
|
25 |
"tokenizer_class": "GPT2Tokenizer",
|
26 |
"unk_token": ""
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "0 ",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"1": {
|
13 |
+
"content": "1 ",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
|
|
18 |
"special": true
|
19 |
}
|
20 |
},
|
21 |
+
"bos_token": "0 ",
|
22 |
"clean_up_tokenization_spaces": false,
|
23 |
+
"eos_token": "1 ",
|
24 |
"model_max_length": 1000000000000000019884624838656,
|
25 |
"tokenizer_class": "GPT2Tokenizer",
|
26 |
"unk_token": ""
|