Upload tokenizer
Browse files- special_tokens_map.json +2 -7
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -1,12 +1,7 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
-
"eos_token":
|
4 |
-
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
"unk_token": {
|
11 |
"content": "<unk>",
|
12 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
5 |
"unk_token": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -31,7 +31,7 @@
|
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": true,
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
-
"pad_token":
|
35 |
"sp_model_kwargs": {},
|
36 |
"spaces_between_special_tokens": false,
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": true,
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "<s>",
|
35 |
"sp_model_kwargs": {},
|
36 |
"spaces_between_special_tokens": false,
|
37 |
"tokenizer_class": "LlamaTokenizer",
|