Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -9
- tokenizer_config.json +1 -9
special_tokens_map.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
-
"unk_token": "unk"
|
5 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
}
|
tokenizer.json
CHANGED
@@ -29,15 +29,6 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 6573,
|
35 |
-
"content": "unk",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"special": true
|
41 |
}
|
42 |
],
|
43 |
"normalizer": null,
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -26,14 +26,6 @@
|
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
29 |
-
},
|
30 |
-
"6573": {
|
31 |
-
"content": "unk",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
}
|
38 |
},
|
39 |
"bos_token": "<s>",
|
@@ -41,5 +33,5 @@
|
|
41 |
"eos_token": "</s>",
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
44 |
-
"unk_token": "unk"
|
45 |
}
|
|
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|
|
|
33 |
"eos_token": "</s>",
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
36 |
+
"unk_token": "<unk>"
|
37 |
}
|