Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
|
|
|
| 4 |
"unk_token": "<unk>"
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "</s>",
|
| 5 |
"unk_token": "<unk>"
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"model_max_length": 1000000000000000019884624838656,
|
| 33 |
-
"pad_token":
|
| 34 |
"sp_model_kwargs": {},
|
| 35 |
"tokenizer_class": "LlamaTokenizer",
|
| 36 |
"unk_token": "<unk>",
|
|
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"model_max_length": 1000000000000000019884624838656,
|
| 33 |
+
"pad_token": "</s>",
|
| 34 |
"sp_model_kwargs": {},
|
| 35 |
"tokenizer_class": "LlamaTokenizer",
|
| 36 |
"unk_token": "<unk>",
|