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
|
@@ -2168,7 +2168,6 @@
|
|
| 2168 |
"clean_up_tokenization_spaces": false,
|
| 2169 |
"cls_token": "[CLS]",
|
| 2170 |
"eos_token": "<|endoftext|>",
|
| 2171 |
-
"extra_special_tokens": {},
|
| 2172 |
"fast_tokenizer": true,
|
| 2173 |
"gmask_token": "[gMASK]",
|
| 2174 |
"merges_file": null,
|
|
@@ -2178,6 +2177,7 @@
|
|
| 2178 |
],
|
| 2179 |
"model_max_length": 1000000000000000019884624838656,
|
| 2180 |
"pad_token": "<|endoftext|>",
|
| 2181 |
-
"tokenizer_class": "
|
| 2182 |
-
"trust_remote_code": true
|
|
|
|
| 2183 |
}
|
|
|
|
| 2168 |
"clean_up_tokenization_spaces": false,
|
| 2169 |
"cls_token": "[CLS]",
|
| 2170 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 2171 |
"fast_tokenizer": true,
|
| 2172 |
"gmask_token": "[gMASK]",
|
| 2173 |
"merges_file": null,
|
|
|
|
| 2177 |
],
|
| 2178 |
"model_max_length": 1000000000000000019884624838656,
|
| 2179 |
"pad_token": "<|endoftext|>",
|
| 2180 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2181 |
+
"trust_remote_code": true,
|
| 2182 |
+
"vocab_file": null
|
| 2183 |
}
|