Upload tokenizer
Browse files- tokenizer_config.json +8 -0
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<pad>",
|
|
@@ -931,9 +932,16 @@
|
|
| 931 |
"eos_token": "</s>",
|
| 932 |
"extra_ids": 100,
|
| 933 |
"extra_special_tokens": {},
|
|
|
|
| 934 |
"model_max_length": 512,
|
|
|
|
| 935 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 936 |
"sp_model_kwargs": {},
|
|
|
|
| 937 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
|
|
| 938 |
"unk_token": "<unk>"
|
| 939 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<pad>",
|
|
|
|
| 932 |
"eos_token": "</s>",
|
| 933 |
"extra_ids": 100,
|
| 934 |
"extra_special_tokens": {},
|
| 935 |
+
"max_length": 1024,
|
| 936 |
"model_max_length": 512,
|
| 937 |
+
"pad_to_multiple_of": null,
|
| 938 |
"pad_token": "<pad>",
|
| 939 |
+
"pad_token_type_id": 0,
|
| 940 |
+
"padding_side": "right",
|
| 941 |
"sp_model_kwargs": {},
|
| 942 |
+
"stride": 0,
|
| 943 |
"tokenizer_class": "T5Tokenizer",
|
| 944 |
+
"truncation_side": "right",
|
| 945 |
+
"truncation_strategy": "longest_first",
|
| 946 |
"unk_token": "<unk>"
|
| 947 |
}
|