Commit
•
43e32db
1
Parent(s):
2b2582c
Upload tokenizer
Browse files- special_tokens_map.json +4 -28
- tokenizer_config.json +0 -4
special_tokens_map.json
CHANGED
|
@@ -5,32 +5,8 @@
|
|
| 5 |
"</s>",
|
| 6 |
"<unk>"
|
| 7 |
],
|
| 8 |
-
"bos_token":
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
"rstrip": false,
|
| 13 |
-
"single_word": false
|
| 14 |
-
},
|
| 15 |
-
"eos_token": {
|
| 16 |
-
"content": "</s>",
|
| 17 |
-
"lstrip": false,
|
| 18 |
-
"normalized": false,
|
| 19 |
-
"rstrip": false,
|
| 20 |
-
"single_word": false
|
| 21 |
-
},
|
| 22 |
-
"pad_token": {
|
| 23 |
-
"content": "<pad>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false
|
| 28 |
-
},
|
| 29 |
-
"unk_token": {
|
| 30 |
-
"content": "<unk>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false
|
| 35 |
-
}
|
| 36 |
}
|
|
|
|
| 5 |
"</s>",
|
| 6 |
"<unk>"
|
| 7 |
],
|
| 8 |
+
"bos_token": "<s>",
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
}
|
tokenizer_config.json
CHANGED
|
@@ -42,10 +42,6 @@
|
|
| 42 |
"bos_token": "<s>",
|
| 43 |
"clean_up_tokenization_spaces": true,
|
| 44 |
"eos_token": "</s>",
|
| 45 |
-
"model_input_names": [
|
| 46 |
-
"input_ids",
|
| 47 |
-
"attention_mask"
|
| 48 |
-
],
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"pad_token": "<pad>",
|
| 51 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
| 42 |
"bos_token": "<s>",
|
| 43 |
"clean_up_tokenization_spaces": true,
|
| 44 |
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"model_max_length": 1000000000000000019884624838656,
|
| 46 |
"pad_token": "<pad>",
|
| 47 |
"tokenizer_class": "PreTrainedTokenizerFast",
|