Upload tokenizer files
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +0 -4
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 4094,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -933,7 +933,6 @@
|
|
| 933 |
"cls_token": "[CLS]",
|
| 934 |
"extra_special_tokens": {},
|
| 935 |
"mask_token": "[MASK]",
|
| 936 |
-
"max_length": 4094,
|
| 937 |
"model_input_names": [
|
| 938 |
"input_ids",
|
| 939 |
"attention_mask"
|
|
@@ -941,9 +940,6 @@
|
|
| 941 |
"model_max_length": 8192,
|
| 942 |
"pad_token": "[PAD]",
|
| 943 |
"sep_token": "[SEP]",
|
| 944 |
-
"stride": 0,
|
| 945 |
"tokenizer_class": "PreTrainedTokenizer",
|
| 946 |
-
"truncation_side": "right",
|
| 947 |
-
"truncation_strategy": "longest_first",
|
| 948 |
"unk_token": "[UNK]"
|
| 949 |
}
|
|
|
|
| 933 |
"cls_token": "[CLS]",
|
| 934 |
"extra_special_tokens": {},
|
| 935 |
"mask_token": "[MASK]",
|
|
|
|
| 936 |
"model_input_names": [
|
| 937 |
"input_ids",
|
| 938 |
"attention_mask"
|
|
|
|
| 940 |
"model_max_length": 8192,
|
| 941 |
"pad_token": "[PAD]",
|
| 942 |
"sep_token": "[SEP]",
|
|
|
|
| 943 |
"tokenizer_class": "PreTrainedTokenizer",
|
|
|
|
|
|
|
| 944 |
"unk_token": "[UNK]"
|
| 945 |
}
|