Upload tokenizer_config.json
Browse files- tokenizer_config.json +2 -21
tokenizer_config.json
CHANGED
|
@@ -25,34 +25,15 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "<|endthought|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"32001": {
|
| 38 |
-
"content": "<|startthought|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
}
|
| 45 |
},
|
| 46 |
-
"additional_special_tokens": [
|
| 47 |
-
"<|endthought|>",
|
| 48 |
-
"<|startthought|>"
|
| 49 |
-
],
|
| 50 |
"bos_token": "<s>",
|
| 51 |
"clean_up_tokenization_spaces": false,
|
| 52 |
"eos_token": "</s>",
|
| 53 |
"legacy": true,
|
| 54 |
"model_max_length": 1000000000000000019884624838656,
|
| 55 |
-
"pad_token":
|
| 56 |
"sp_model_kwargs": {},
|
| 57 |
"spaces_between_special_tokens": false,
|
| 58 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"legacy": true,
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": null,
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|