Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +7 -0
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
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,
|
tokenizer_config.json
CHANGED
@@ -3960,12 +3960,19 @@
|
|
3960 |
"clean_up_tokenization_spaces": false,
|
3961 |
"eos_token": "</s>",
|
3962 |
"fast": true,
|
|
|
3963 |
"model_max_length": 1024,
|
|
|
3964 |
"pad_token": "</s>",
|
|
|
|
|
3965 |
"padding_size": "right",
|
3966 |
"sp_model_kwargs": {},
|
3967 |
"spaces_between_special_tokens": false,
|
|
|
3968 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
3969 |
"unk_token": "<unk>",
|
3970 |
"use_default_system_prompt": true
|
3971 |
}
|
|
|
3960 |
"clean_up_tokenization_spaces": false,
|
3961 |
"eos_token": "</s>",
|
3962 |
"fast": true,
|
3963 |
+
"max_length": 1024,
|
3964 |
"model_max_length": 1024,
|
3965 |
+
"pad_to_multiple_of": null,
|
3966 |
"pad_token": "</s>",
|
3967 |
+
"pad_token_type_id": 0,
|
3968 |
+
"padding_side": "left",
|
3969 |
"padding_size": "right",
|
3970 |
"sp_model_kwargs": {},
|
3971 |
"spaces_between_special_tokens": false,
|
3972 |
+
"stride": 0,
|
3973 |
"tokenizer_class": "LlamaTokenizer",
|
3974 |
+
"truncation_side": "right",
|
3975 |
+
"truncation_strategy": "longest_first",
|
3976 |
"unk_token": "<unk>",
|
3977 |
"use_default_system_prompt": true
|
3978 |
}
|