Upload tokenizer
Browse files- special_tokens_map.json +5 -4
- tokenizer.json +0 -0
- tokenizer_config.json +1 -5
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"pad_token": "
|
| 5 |
-
"
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
-
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 512,
|
| 7 |
-
"tokenizer_class": "
|
| 8 |
-
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 3 |
"model_max_length": 512,
|
| 4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 5 |
}
|