fr
Browse files- tokenizer_config.json +32 -6
tokenizer_config.json
CHANGED
|
@@ -1,10 +1,36 @@
|
|
| 1 |
{
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"tokenizer_class": "OBITokenizer",
|
| 4 |
-
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": ["tokenizerConfig.OBITokenizer", null]
|
| 4 |
+
},
|
| 5 |
+
"add_bos_token": false,
|
| 6 |
+
"add_eos_token": false,
|
| 7 |
+
"use_fast": false,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"__type": "AddedToken",
|
| 11 |
+
"content": "</s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": true
|
| 16 |
+
},
|
| 17 |
+
"model_max_length": 4096,
|
| 18 |
+
"sp_model_kwargs": {},
|
| 19 |
"tokenizer_class": "OBITokenizer",
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"__type": "AddedToken",
|
| 22 |
+
"content": "<unk>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": true
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": true
|
| 35 |
}
|
| 36 |
}
|