Upload tokenizer
Browse files- special_tokens_map.json +0 -7
- tokenizer.json +0 -27
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
|
@@ -13,13 +13,6 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "</s>",
|
| 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 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -52,12 +52,6 @@
|
|
| 52 |
"id": "A",
|
| 53 |
"type_id": 0
|
| 54 |
}
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"SpecialToken": {
|
| 58 |
-
"id": "</s>",
|
| 59 |
-
"type_id": 0
|
| 60 |
-
}
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"pair": [
|
|
@@ -73,12 +67,6 @@
|
|
| 73 |
"type_id": 0
|
| 74 |
}
|
| 75 |
},
|
| 76 |
-
{
|
| 77 |
-
"SpecialToken": {
|
| 78 |
-
"id": "</s>",
|
| 79 |
-
"type_id": 0
|
| 80 |
-
}
|
| 81 |
-
},
|
| 82 |
{
|
| 83 |
"SpecialToken": {
|
| 84 |
"id": "<s>",
|
|
@@ -90,24 +78,9 @@
|
|
| 90 |
"id": "B",
|
| 91 |
"type_id": 1
|
| 92 |
}
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"SpecialToken": {
|
| 96 |
-
"id": "</s>",
|
| 97 |
-
"type_id": 1
|
| 98 |
-
}
|
| 99 |
}
|
| 100 |
],
|
| 101 |
"special_tokens": {
|
| 102 |
-
"</s>": {
|
| 103 |
-
"id": "</s>",
|
| 104 |
-
"ids": [
|
| 105 |
-
2
|
| 106 |
-
],
|
| 107 |
-
"tokens": [
|
| 108 |
-
"</s>"
|
| 109 |
-
]
|
| 110 |
-
},
|
| 111 |
"<s>": {
|
| 112 |
"id": "<s>",
|
| 113 |
"ids": [
|
|
|
|
| 52 |
"id": "A",
|
| 53 |
"type_id": 0
|
| 54 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"pair": [
|
|
|
|
| 67 |
"type_id": 0
|
| 68 |
}
|
| 69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{
|
| 71 |
"SpecialToken": {
|
| 72 |
"id": "<s>",
|
|
|
|
| 78 |
"id": "B",
|
| 79 |
"type_id": 1
|
| 80 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
}
|
| 82 |
],
|
| 83 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
"<s>": {
|
| 85 |
"id": "<s>",
|
| 86 |
"ids": [
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
-
"add_eos_token":
|
| 4 |
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
|
@@ -35,7 +35,7 @@
|
|
| 35 |
"extra_special_tokens": {},
|
| 36 |
"legacy": false,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
-
"pad_token":
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
|
|
|
| 35 |
"extra_special_tokens": {},
|
| 36 |
"legacy": false,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": null,
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|