Update tokenizer config
Browse files- special_tokens_map.json +4 -1
- tokenizer_config.json +3 -1
special_tokens_map.json
CHANGED
|
@@ -1 +1,4 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>"
|
| 4 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -8025,10 +8025,12 @@
|
|
| 8025 |
"special": false
|
| 8026 |
}
|
| 8027 |
},
|
|
|
|
| 8028 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 8029 |
"model_input_names": [
|
| 8030 |
"input_ids",
|
| 8031 |
-
"
|
| 8032 |
],
|
| 8033 |
"model_max_length": 1000000000000000019884624838656,
|
| 8034 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 8025 |
"special": false
|
| 8026 |
}
|
| 8027 |
},
|
| 8028 |
+
"bos_token": "<s>",
|
| 8029 |
"clean_up_tokenization_spaces": true,
|
| 8030 |
+
"eos_token": "</s>",
|
| 8031 |
"model_input_names": [
|
| 8032 |
"input_ids",
|
| 8033 |
+
"attention_mask"
|
| 8034 |
],
|
| 8035 |
"model_max_length": 1000000000000000019884624838656,
|
| 8036 |
"tokenizer_class": "PreTrainedTokenizerFast"
|