Upload tokenizer
Browse files- special_tokens_map.json +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +2 -11
special_tokens_map.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"bos_token": "|<BOS>|",
|
3 |
"eos_token": "|<EOS>|",
|
4 |
"pad_token": "|<PAD>|"
|
5 |
}
|
|
|
1 |
{
|
|
|
2 |
"eos_token": "|<EOS>|",
|
3 |
"pad_token": "|<PAD>|"
|
4 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "|<BOS>|",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
"content": "|<EOS>|",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,7 +8,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "|<UNK>|",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +16,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "|<PAD>|",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -33,7 +25,6 @@
|
|
33 |
"special": true
|
34 |
}
|
35 |
},
|
36 |
-
"bos_token": "|<BOS>|",
|
37 |
"clean_up_tokenization_spaces": true,
|
38 |
"eos_token": "|<EOS>|",
|
39 |
"max_length": null,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"content": "|<EOS>|",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
"content": "|<UNK>|",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
"content": "|<PAD>|",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
|
|
28 |
"clean_up_tokenization_spaces": true,
|
29 |
"eos_token": "|<EOS>|",
|
30 |
"max_length": null,
|