Commit
·
198d4f4
1
Parent(s):
a2e7497
Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<cls>",
|
| 4 |
+
"eos_token": "</s>",
|
| 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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_max_length": 1024,
|
| 3 |
+
"name_or_path": "/home/shohan/Dev/PlayGround/BanglaTokenizer/BengaliSentencePieceBPETokenizerFast",
|
| 4 |
+
"special_tokens": [
|
| 5 |
+
"<s>",
|
| 6 |
+
"<pad>",
|
| 7 |
+
"</s>",
|
| 8 |
+
"<unk>",
|
| 9 |
+
"<cls>",
|
| 10 |
+
"<sep>",
|
| 11 |
+
"<mask>"
|
| 12 |
+
],
|
| 13 |
+
"special_tokens_map_file": "/home/shohan/Dev/PlayGround/BanglaTokenizer/BengaliSentencePieceBPETokenizerFast/special_tokens_map.json",
|
| 14 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 15 |
+
}
|