Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +3 -3
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -2145,7 +2145,6 @@
|
|
| 2145 |
"clean_up_tokenization_spaces": false,
|
| 2146 |
"cls_token": "[CLS]",
|
| 2147 |
"eos_token": "<|endoftext|>",
|
| 2148 |
-
"extra_special_tokens": {},
|
| 2149 |
"fast_tokenizer": true,
|
| 2150 |
"gmask_token": "[gMASK]",
|
| 2151 |
"merges_file": null,
|
|
@@ -2155,6 +2154,7 @@
|
|
| 2155 |
],
|
| 2156 |
"model_max_length": 1000000000000000019884624838656,
|
| 2157 |
"pad_token": "<|endoftext|>",
|
| 2158 |
-
"tokenizer_class": "
|
| 2159 |
-
"trust_remote_code": true
|
|
|
|
| 2160 |
}
|
|
|
|
| 2145 |
"clean_up_tokenization_spaces": false,
|
| 2146 |
"cls_token": "[CLS]",
|
| 2147 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 2148 |
"fast_tokenizer": true,
|
| 2149 |
"gmask_token": "[gMASK]",
|
| 2150 |
"merges_file": null,
|
|
|
|
| 2154 |
],
|
| 2155 |
"model_max_length": 1000000000000000019884624838656,
|
| 2156 |
"pad_token": "<|endoftext|>",
|
| 2157 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2158 |
+
"trust_remote_code": true,
|
| 2159 |
+
"vocab_file": null
|
| 2160 |
}
|