Update tokenizer_config.json
Browse files- tokenizer_config.json +6 -8
tokenizer_config.json
CHANGED
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
-
"content": "",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": true,
|
| 17 |
"rstrip": false,
|
|
@@ -19,7 +19,7 @@
|
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
-
"content": "",
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": true,
|
| 25 |
"rstrip": false,
|
|
@@ -28,13 +28,11 @@
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"auto_map": {
|
| 31 |
-
"AutoTokenizer": [
|
| 32 |
-
"tokenization_yi.YiTokenizer", null
|
| 33 |
-
]
|
| 34 |
},
|
| 35 |
-
"bos_token": "",
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
-
"eos_token": "",
|
| 38 |
"model_max_length": 4096,
|
| 39 |
"pad_token": "<unk>",
|
| 40 |
"padding_side": "left",
|
|
@@ -42,4 +40,4 @@
|
|
| 42 |
"split_special_tokens": false,
|
| 43 |
"tokenizer_class": "YiTokenizer",
|
| 44 |
"unk_token": "<unk>"
|
| 45 |
-
}
|
|
|
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
+
"content": "<|startoftext|>",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": true,
|
| 17 |
"rstrip": false,
|
|
|
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": true,
|
| 25 |
"rstrip": false,
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"auto_map": {
|
| 31 |
+
"AutoTokenizer": ["tokenization_yi.YiTokenizer",null]
|
|
|
|
|
|
|
| 32 |
},
|
| 33 |
+
"bos_token": "<|startoftext|>",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "<|endoftext|>",
|
| 36 |
"model_max_length": 4096,
|
| 37 |
"pad_token": "<unk>",
|
| 38 |
"padding_side": "left",
|
|
|
|
| 40 |
"split_special_tokens": false,
|
| 41 |
"tokenizer_class": "YiTokenizer",
|
| 42 |
"unk_token": "<unk>"
|
| 43 |
+
}
|