Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +4 -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
@@ -35,11 +35,15 @@
|
|
35 |
"eos_token": "</s>",
|
36 |
"extra_special_tokens": {},
|
37 |
"legacy": false,
|
|
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
39 |
"pad_token": "</s>",
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
|
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
43 |
"unk_token": "<unk>",
|
44 |
"use_default_system_prompt": false
|
45 |
}
|
|
|
35 |
"eos_token": "</s>",
|
36 |
"extra_special_tokens": {},
|
37 |
"legacy": false,
|
38 |
+
"max_length": 1024,
|
39 |
"model_max_length": 1000000000000000019884624838656,
|
40 |
"pad_token": "</s>",
|
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 |
}
|