add tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"keep_accents": true,
|
| 7 |
+
"mask_token": {
|
| 8 |
+
"__type": "AddedToken",
|
| 9 |
+
"content": "[MASK]",
|
| 10 |
+
"lstrip": true,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"name_or_path": "checkpoints/tokenizer8",
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"remove_space": true,
|
| 18 |
+
"sep_token": "[SEP]",
|
| 19 |
+
"sp_model_kwargs": {},
|
| 20 |
+
"special_tokens_map_file": "/content/drive/MyDrive/ColabModels/GPT2_MEDIUM/pytorch_model/special_tokens_map.json",
|
| 21 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 22 |
+
"unk_token": "<unk>"
|
| 23 |
+
}
|