Update tokenizer_config.json
#2
by
saattrupdan
- opened
- tokenizer_config.json +3 -46
tokenizer_config.json
CHANGED
|
@@ -26,57 +26,14 @@
|
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "<CLS>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"32001": {
|
| 38 |
-
"content": "<SEP>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"32002": {
|
| 46 |
-
"content": "<EOD>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"32003": {
|
| 54 |
-
"content": "<MASK>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"32004": {
|
| 62 |
-
"content": "<PAD>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
}
|
| 69 |
},
|
| 70 |
"bos_token": "<s>",
|
| 71 |
"clean_up_tokenization_spaces": false,
|
| 72 |
-
"cls_token": "<CLS>",
|
| 73 |
"eos_token": "</s>",
|
| 74 |
"legacy": false,
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"padding_side": "right",
|
| 79 |
-
"sep_token": "<SEP>",
|
| 80 |
"sp_model_kwargs": {},
|
| 81 |
"tokenizer_class": "LlamaTokenizer",
|
| 82 |
"unk_token": "<unk>",
|
|
|
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
},
|
| 30 |
"bos_token": "<s>",
|
| 31 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": false,
|
| 34 |
+
"model_max_length": 4096,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"padding_side": "left",
|
|
|
|
|
|
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
"unk_token": "<unk>",
|