Commit
•
86527f1
1
Parent(s):
e5f6219
Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer_config.json +0 -4
special_tokens_map.json
CHANGED
|
@@ -13,13 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
| 17 |
-
"content": "</s>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -32,15 +32,11 @@
|
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"legacy": false,
|
| 35 |
-
"max_length": 1024,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"padding_side": "right",
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
-
"stride": 0,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
-
"truncation_side": "right",
|
| 43 |
-
"truncation_strategy": "longest_first",
|
| 44 |
"unk_token": "<unk>",
|
| 45 |
"use_default_system_prompt": false
|
| 46 |
}
|
|
|
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"legacy": false,
|
|
|
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
"pad_token": "</s>",
|
| 37 |
"padding_side": "right",
|
| 38 |
"sp_model_kwargs": {},
|
|
|
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 40 |
"unk_token": "<unk>",
|
| 41 |
"use_default_system_prompt": false
|
| 42 |
}
|