Upload tokenizer
Browse files- special_tokens_map.json +2 -14
- tokenizer.json +1 -1
- tokenizer_config.json +2 -4
special_tokens_map.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "<image>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
}
|
| 17 |
],
|
| 18 |
"bos_token": {
|
| 19 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<image>",
|
| 4 |
+
"<fake_token_around_image>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<s>",
|
tokenizer.json
CHANGED
|
@@ -31506,7 +31506,7 @@
|
|
| 31506 |
"अ": 31350,
|
| 31507 |
"╔": 31351,
|
| 31508 |
"无": 31352,
|
| 31509 |
-
"
|
| 31510 |
"은": 31354,
|
| 31511 |
"ʷ": 31355,
|
| 31512 |
"那": 31356,
|
|
|
|
| 31506 |
"अ": 31350,
|
| 31507 |
"╔": 31351,
|
| 31508 |
"无": 31352,
|
| 31509 |
+
"
|
| 31510 |
"은": 31354,
|
| 31511 |
"ʷ": 31355,
|
| 31512 |
"那": 31356,
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -44,8 +42,8 @@
|
|
| 44 |
}
|
| 45 |
},
|
| 46 |
"additional_special_tokens": [
|
| 47 |
-
"<
|
| 48 |
-
"<
|
| 49 |
],
|
| 50 |
"bos_token": "<s>",
|
| 51 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"additional_special_tokens": [
|
| 45 |
+
"<image>",
|
| 46 |
+
"<fake_token_around_image>"
|
| 47 |
],
|
| 48 |
"bos_token": "<s>",
|
| 49 |
"clean_up_tokenization_spaces": false,
|