Commit
·
0e1c2c5
1
Parent(s):
48eb1bb
Upload tokenizer
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -33,11 +33,15 @@
|
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|
|
|
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|
|
|
|
| 40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 41 |
"unk_token": "<unk>",
|
| 42 |
"use_default_system_prompt": false
|
| 43 |
}
|
|
|
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|
| 36 |
+
"max_length": 512,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
"pad_token": "</s>",
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
+
"stride": 0,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"truncation_side": "right",
|
| 44 |
+
"truncation_strategy": "longest_first",
|
| 45 |
"unk_token": "<unk>",
|
| 46 |
"use_default_system_prompt": false
|
| 47 |
}
|