Upload tokenizer
Browse files- tokenizer.json +6 -28
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
@@ -62,12 +67,6 @@
|
|
| 62 |
"id": "A",
|
| 63 |
"type_id": 0
|
| 64 |
}
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"SpecialToken": {
|
| 68 |
-
"id": "</s>",
|
| 69 |
-
"type_id": 0
|
| 70 |
-
}
|
| 71 |
}
|
| 72 |
],
|
| 73 |
"pair": [
|
|
@@ -83,12 +82,6 @@
|
|
| 83 |
"type_id": 0
|
| 84 |
}
|
| 85 |
},
|
| 86 |
-
{
|
| 87 |
-
"SpecialToken": {
|
| 88 |
-
"id": "</s>",
|
| 89 |
-
"type_id": 0
|
| 90 |
-
}
|
| 91 |
-
},
|
| 92 |
{
|
| 93 |
"SpecialToken": {
|
| 94 |
"id": "<s>",
|
|
@@ -100,24 +93,9 @@
|
|
| 100 |
"id": "B",
|
| 101 |
"type_id": 1
|
| 102 |
}
|
| 103 |
-
},
|
| 104 |
-
{
|
| 105 |
-
"SpecialToken": {
|
| 106 |
-
"id": "</s>",
|
| 107 |
-
"type_id": 1
|
| 108 |
-
}
|
| 109 |
}
|
| 110 |
],
|
| 111 |
"special_tokens": {
|
| 112 |
-
"</s>": {
|
| 113 |
-
"id": "</s>",
|
| 114 |
-
"ids": [
|
| 115 |
-
2
|
| 116 |
-
],
|
| 117 |
-
"tokens": [
|
| 118 |
-
"</s>"
|
| 119 |
-
]
|
| 120 |
-
},
|
| 121 |
"<s>": {
|
| 122 |
"id": "<s>",
|
| 123 |
"ids": [
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 67 |
"id": "A",
|
| 68 |
"type_id": 0
|
| 69 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
}
|
| 71 |
],
|
| 72 |
"pair": [
|
|
|
|
| 82 |
"type_id": 0
|
| 83 |
}
|
| 84 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
{
|
| 86 |
"SpecialToken": {
|
| 87 |
"id": "<s>",
|
|
|
|
| 93 |
"id": "B",
|
| 94 |
"type_id": 1
|
| 95 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
}
|
| 97 |
],
|
| 98 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
"<s>": {
|
| 100 |
"id": "<s>",
|
| 101 |
"ids": [
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
-
"add_eos_token":
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -35,7 +35,6 @@
|
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
-
"padding_side": "left",
|
| 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 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": "</s>",
|
|
|
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|
| 40 |
"tokenizer_class": "LlamaTokenizer",
|