Add tokenizer_config.json required by fastembed-rs tokenizer loader
Browse files- tokenizer_config.json +29 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
+
"cls_token": null,
|
| 21 |
+
"do_lower_case": true,
|
| 22 |
+
"mask_token": null,
|
| 23 |
+
"model_max_length": 1000000,
|
| 24 |
+
"pad_token": "[PAD]",
|
| 25 |
+
"sep_token": null,
|
| 26 |
+
"tokenize_chinese_chars": true,
|
| 27 |
+
"tokenizer_class": "BertTokenizer",
|
| 28 |
+
"unk_token": "[UNK]"
|
| 29 |
+
}
|