Upload tokenizer
Browse files- tokenizer.json +2 -7
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
@@ -148,7 +143,7 @@
|
|
| 148 |
"pre_tokenizer": {
|
| 149 |
"type": "Metaspace",
|
| 150 |
"replacement": "▁",
|
| 151 |
-
"prepend_scheme": "
|
| 152 |
"split": false
|
| 153 |
},
|
| 154 |
"post_processor": {
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 143 |
"pre_tokenizer": {
|
| 144 |
"type": "Metaspace",
|
| 145 |
"replacement": "▁",
|
| 146 |
+
"prepend_scheme": "first",
|
| 147 |
"split": false
|
| 148 |
},
|
| 149 |
"post_processor": {
|
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<｜end▁of▁sentence｜>",
|
| 7 |
-
"is_local":
|
| 8 |
"model_max_length": 4096,
|
| 9 |
"pad_token": "<｜end▁of▁sentence｜>",
|
| 10 |
"sp_model_kwargs": {},
|
|
|
|
| 4 |
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<｜end▁of▁sentence｜>",
|
| 7 |
+
"is_local": true,
|
| 8 |
"model_max_length": 4096,
|
| 9 |
"pad_token": "<｜end▁of▁sentence｜>",
|
| 10 |
"sp_model_kwargs": {},
|