Upload tokenizer
Browse files- added_tokens.json +52 -0
- merges.txt +0 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<col0>": 50265,
|
| 3 |
+
"<col10>": 50275,
|
| 4 |
+
"<col11>": 50276,
|
| 5 |
+
"<col12>": 50277,
|
| 6 |
+
"<col13>": 50278,
|
| 7 |
+
"<col14>": 50279,
|
| 8 |
+
"<col15>": 50280,
|
| 9 |
+
"<col16>": 50281,
|
| 10 |
+
"<col17>": 50282,
|
| 11 |
+
"<col18>": 50283,
|
| 12 |
+
"<col19>": 50284,
|
| 13 |
+
"<col1>": 50266,
|
| 14 |
+
"<col20>": 50285,
|
| 15 |
+
"<col21>": 50286,
|
| 16 |
+
"<col22>": 50287,
|
| 17 |
+
"<col23>": 50288,
|
| 18 |
+
"<col24>": 50289,
|
| 19 |
+
"<col25>": 50290,
|
| 20 |
+
"<col26>": 50291,
|
| 21 |
+
"<col27>": 50292,
|
| 22 |
+
"<col28>": 50293,
|
| 23 |
+
"<col29>": 50294,
|
| 24 |
+
"<col2>": 50267,
|
| 25 |
+
"<col30>": 50295,
|
| 26 |
+
"<col31>": 50296,
|
| 27 |
+
"<col32>": 50297,
|
| 28 |
+
"<col33>": 50298,
|
| 29 |
+
"<col34>": 50299,
|
| 30 |
+
"<col35>": 50300,
|
| 31 |
+
"<col36>": 50301,
|
| 32 |
+
"<col37>": 50302,
|
| 33 |
+
"<col38>": 50303,
|
| 34 |
+
"<col39>": 50304,
|
| 35 |
+
"<col3>": 50268,
|
| 36 |
+
"<col40>": 50305,
|
| 37 |
+
"<col41>": 50306,
|
| 38 |
+
"<col42>": 50307,
|
| 39 |
+
"<col43>": 50308,
|
| 40 |
+
"<col44>": 50309,
|
| 41 |
+
"<col45>": 50310,
|
| 42 |
+
"<col46>": 50311,
|
| 43 |
+
"<col47>": 50312,
|
| 44 |
+
"<col48>": 50313,
|
| 45 |
+
"<col49>": 50314,
|
| 46 |
+
"<col4>": 50269,
|
| 47 |
+
"<col5>": 50270,
|
| 48 |
+
"<col6>": 50271,
|
| 49 |
+
"<col7>": 50272,
|
| 50 |
+
"<col8>": 50273,
|
| 51 |
+
"<col9>": 50274
|
| 52 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"name_or_path": "shahrukhx01/schema-aware-denoising-bart-large-cnn-text2sql",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "BartTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|