Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +34 -0
- tokenizer_config.json +6 -0
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [],
|
6 |
+
"normalizer": {
|
7 |
+
"type": "NFKC"
|
8 |
+
},
|
9 |
+
"pre_tokenizer": {
|
10 |
+
"type": "Metaspace",
|
11 |
+
"replacement": "▁",
|
12 |
+
"prepend_scheme": "always",
|
13 |
+
"split": true
|
14 |
+
},
|
15 |
+
"post_processor": null,
|
16 |
+
"decoder": {
|
17 |
+
"type": "Metaspace",
|
18 |
+
"replacement": "▁",
|
19 |
+
"prepend_scheme": "always",
|
20 |
+
"split": true
|
21 |
+
},
|
22 |
+
"model": {
|
23 |
+
"type": "BPE",
|
24 |
+
"dropout": null,
|
25 |
+
"unk_token": "<unk>",
|
26 |
+
"continuing_subword_prefix": null,
|
27 |
+
"end_of_word_suffix": null,
|
28 |
+
"fuse_unk": false,
|
29 |
+
"byte_fallback": false,
|
30 |
+
"ignore_merges": false,
|
31 |
+
"vocab": {},
|
32 |
+
"merges": []
|
33 |
+
}
|
34 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {},
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"model_max_length": 1000000000000000019884624838656,
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
+
}
|