Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,5 +13,11 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
}
|
tokenizer_config.json
CHANGED
|
@@ -185,7 +185,7 @@
|
|
| 185 |
"eos_token": "<|EOT|>",
|
| 186 |
"legacy": true,
|
| 187 |
"model_max_length": 16384,
|
| 188 |
-
"pad_token": "
|
| 189 |
"sp_model_kwargs": {},
|
| 190 |
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
"unk_token": null,
|
|
|
|
| 185 |
"eos_token": "<|EOT|>",
|
| 186 |
"legacy": true,
|
| 187 |
"model_max_length": 16384,
|
| 188 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 189 |
"sp_model_kwargs": {},
|
| 190 |
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
"unk_token": null,
|