Upload tokenizer
Browse files- added_tokens.json +4 -0
- merges.txt +0 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<pad>": 1
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<pad>",
|
4 |
+
"</s>"
|
5 |
+
],
|
6 |
+
"bos_token": "</s>",
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"unk_token": "</s>"
|
10 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"1": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"2": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"additional_special_tokens": [
|
23 |
+
"<pad>",
|
24 |
+
"</s>"
|
25 |
+
],
|
26 |
+
"bos_token": "</s>",
|
27 |
+
"clean_up_tokenization_spaces": true,
|
28 |
+
"eos_token": "</s>",
|
29 |
+
"errors": "replace",
|
30 |
+
"max_length": 512,
|
31 |
+
"model_max_length": 1000000000000000019884624838656,
|
32 |
+
"pad_to_multiple_of": null,
|
33 |
+
"pad_token": "<pad>",
|
34 |
+
"pad_token_type_id": 0,
|
35 |
+
"padding_side": "right",
|
36 |
+
"stride": 0,
|
37 |
+
"tokenizer_class": "GPT2Tokenizer",
|
38 |
+
"truncation_side": "right",
|
39 |
+
"truncation_strategy": "longest_first",
|
40 |
+
"unk_token": "</s>"
|
41 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|