Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +23 -3
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"eos_token": "[EOS]",
|
| 4 |
-
"
|
| 5 |
-
"model_max_length":
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[EOS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
+
"clean_up_tokenization_spaces": false,
|
| 21 |
"eos_token": "[EOS]",
|
| 22 |
+
"extra_special_tokens": {},
|
| 23 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 24 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 25 |
+
"unk_token": "[UNK]"
|
| 26 |
}
|