Upload tokenizer
Browse files- tokenizer.json +2 -14
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 1,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "</s>"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -955,9 +955,16 @@
|
|
| 955 |
"eos_token": "</s>",
|
| 956 |
"extra_ids": 100,
|
| 957 |
"legacy": false,
|
|
|
|
| 958 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 959 |
"pad_token": "</s>",
|
|
|
|
|
|
|
| 960 |
"sp_model_kwargs": {},
|
|
|
|
| 961 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
|
|
| 962 |
"unk_token": "<unk>"
|
| 963 |
}
|
|
|
|
| 955 |
"eos_token": "</s>",
|
| 956 |
"extra_ids": 100,
|
| 957 |
"legacy": false,
|
| 958 |
+
"max_length": 1024,
|
| 959 |
"model_max_length": 1000000000000000019884624838656,
|
| 960 |
+
"pad_to_multiple_of": null,
|
| 961 |
"pad_token": "</s>",
|
| 962 |
+
"pad_token_type_id": 0,
|
| 963 |
+
"padding_side": "right",
|
| 964 |
"sp_model_kwargs": {},
|
| 965 |
+
"stride": 0,
|
| 966 |
"tokenizer_class": "T5Tokenizer",
|
| 967 |
+
"truncation_side": "right",
|
| 968 |
+
"truncation_strategy": "longest_first",
|
| 969 |
"unk_token": "<unk>"
|
| 970 |
}
|