Upload tokenizer
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": 2014,
|
| 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
|
@@ -256,12 +256,8 @@
|
|
| 256 |
"cls_token": "<classification>",
|
| 257 |
"eos_token": "<eos>",
|
| 258 |
"extra_special_tokens": {},
|
| 259 |
-
"max_length": 2014,
|
| 260 |
"model_max_length": 1000000000000000019884624838656,
|
| 261 |
"pad_token": "<pad>",
|
| 262 |
-
"stride": 0,
|
| 263 |
"tokenizer_class": "GPT2Tokenizer",
|
| 264 |
-
"truncation_side": "right",
|
| 265 |
-
"truncation_strategy": "longest_first",
|
| 266 |
"unk_token": "<unk>"
|
| 267 |
}
|
|
|
|
| 256 |
"cls_token": "<classification>",
|
| 257 |
"eos_token": "<eos>",
|
| 258 |
"extra_special_tokens": {},
|
|
|
|
| 259 |
"model_max_length": 1000000000000000019884624838656,
|
| 260 |
"pad_token": "<pad>",
|
|
|
|
| 261 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 262 |
"unk_token": "<unk>"
|
| 263 |
}
|