add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +32 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [],
|
| 6 |
+
"normalizer": null,
|
| 7 |
+
"pre_tokenizer": {
|
| 8 |
+
"type": "ByteLevel",
|
| 9 |
+
"add_prefix_space": false,
|
| 10 |
+
"trim_offsets": true
|
| 11 |
+
},
|
| 12 |
+
"post_processor": {
|
| 13 |
+
"type": "ByteLevel",
|
| 14 |
+
"add_prefix_space": true,
|
| 15 |
+
"trim_offsets": false
|
| 16 |
+
},
|
| 17 |
+
"decoder": {
|
| 18 |
+
"type": "ByteLevel",
|
| 19 |
+
"add_prefix_space": true,
|
| 20 |
+
"trim_offsets": true
|
| 21 |
+
},
|
| 22 |
+
"model": {
|
| 23 |
+
"type": "BPE",
|
| 24 |
+
"dropout": null,
|
| 25 |
+
"unk_token": null,
|
| 26 |
+
"continuing_subword_prefix": null,
|
| 27 |
+
"end_of_word_suffix": null,
|
| 28 |
+
"fuse_unk": false,
|
| 29 |
+
"vocab": {},
|
| 30 |
+
"merges": []
|
| 31 |
+
}
|
| 32 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"tokenizer_class": "PreTrainedTokenizerFast"}
|