Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -9
- tokenizer_config.json +1 -10
special_tokens_map.json
CHANGED
|
@@ -19,7 +19,7 @@
|
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"pad_token": {
|
| 22 |
-
"content": "
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
|
|
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -29,15 +29,6 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 32000,
|
| 35 |
-
"content": "[PAD]",
|
| 36 |
-
"single_word": false,
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"rstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -25,14 +25,6 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "[PAD]",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"additional_special_tokens": [
|
|
@@ -46,8 +38,7 @@
|
|
| 46 |
"eos_token": "</s>",
|
| 47 |
"legacy": true,
|
| 48 |
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
-
"pad_token": "
|
| 50 |
-
"padding_side": "right",
|
| 51 |
"sp_model_kwargs": {},
|
| 52 |
"spaces_between_special_tokens": false,
|
| 53 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"additional_special_tokens": [
|
|
|
|
| 38 |
"eos_token": "</s>",
|
| 39 |
"legacy": true,
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
+
"pad_token": "</s>",
|
|
|
|
| 42 |
"sp_model_kwargs": {},
|
| 43 |
"spaces_between_special_tokens": false,
|
| 44 |
"tokenizer_class": "LlamaTokenizer",
|