Upload tokenizer
Browse files- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 64,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
tokenizer_config.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
"errors": "replace",
|
| 7 |
"mask_token": "<mask>",
|
| 8 |
"model_max_length": 512,
|
| 9 |
-
"name_or_path": "cardiffnlp/twitter-roberta-base-
|
| 10 |
"pad_token": "<pad>",
|
| 11 |
"sep_token": "</s>",
|
| 12 |
"special_tokens_map_file": null,
|
|
|
|
| 6 |
"errors": "replace",
|
| 7 |
"mask_token": "<mask>",
|
| 8 |
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "cardiffnlp/twitter-roberta-base-2022-154m",
|
| 10 |
"pad_token": "<pad>",
|
| 11 |
"sep_token": "</s>",
|
| 12 |
"special_tokens_map_file": null,
|