Locutusque
commited on
Commit
•
b6045f5
1
Parent(s):
939c83f
Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
@@ -32,11 +32,18 @@
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
|
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
36 |
"pad_token": "</s>",
|
|
|
|
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
|
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
"use_default_system_prompt": false
|
42 |
}
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
+
"max_length": 512,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_to_multiple_of": null,
|
38 |
"pad_token": "</s>",
|
39 |
+
"pad_token_type_id": 0,
|
40 |
+
"padding_side": "left",
|
41 |
"sp_model_kwargs": {},
|
42 |
"spaces_between_special_tokens": false,
|
43 |
+
"stride": 0,
|
44 |
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"truncation_side": "right",
|
46 |
+
"truncation_strategy": "longest_first",
|
47 |
"unk_token": "<unk>",
|
48 |
"use_default_system_prompt": false
|
49 |
}
|