Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +9 -0
- tokenizer_config.json +10 -1
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 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,
|
tokenizer.json
CHANGED
|
@@ -29,6 +29,15 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 20277,
|
| 35 |
+
"content": "<pad>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -25,6 +25,14 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"additional_special_tokens": [],
|
|
@@ -34,7 +42,8 @@
|
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
-
"pad_token":
|
|
|
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|
| 40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
+
},
|
| 29 |
+
"20277": {
|
| 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": [],
|
|
|
|
| 42 |
"eos_token": "</s>",
|
| 43 |
"legacy": true,
|
| 44 |
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token": "<pad>",
|
| 46 |
+
"pad_token_id": 20277,
|
| 47 |
"sp_model_kwargs": {},
|
| 48 |
"spaces_between_special_tokens": false,
|
| 49 |
"tokenizer_class": "LlamaTokenizer",
|