Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer_config.json +2 -10
special_tokens_map.json
CHANGED
@@ -13,13 +13,7 @@
|
|
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,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
4 |
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
@@ -26,14 +26,6 @@
|
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
29 |
-
},
|
30 |
-
"32000": {
|
31 |
-
"content": "[PAD]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
}
|
38 |
},
|
39 |
"bos_token": "<s>",
|
@@ -41,7 +33,7 @@
|
|
41 |
"eos_token": "</s>",
|
42 |
"legacy": false,
|
43 |
"model_max_length": 1000000000000000019884624838656,
|
44 |
-
"pad_token": "
|
45 |
"padding_side": "right",
|
46 |
"sp_model_kwargs": {},
|
47 |
"spaces_between_special_tokens": false,
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
|
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "<s>",
|
37 |
"padding_side": "right",
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|