Commit
•
352f2fb
1
Parent(s):
92dbccf
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -44
tokenizer_config.json
CHANGED
|
@@ -26,58 +26,15 @@
|
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "▁<PRE>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"32001": {
|
| 38 |
-
"content": "▁<MID>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"32002": {
|
| 46 |
-
"content": "▁<SUF>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"32003": {
|
| 54 |
-
"content": "▁<EOT>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
}
|
| 61 |
},
|
| 62 |
-
"additional_special_tokens": [
|
| 63 |
-
"▁<PRE>",
|
| 64 |
-
"▁<MID>",
|
| 65 |
-
"▁<SUF>",
|
| 66 |
-
"▁<EOT>"
|
| 67 |
-
],
|
| 68 |
"bos_token": "<s>",
|
| 69 |
"clean_up_tokenization_spaces": false,
|
| 70 |
"eos_token": "</s>",
|
| 71 |
-
"eot_token": "▁<EOT>",
|
| 72 |
-
"fill_token": "<FILL_ME>",
|
| 73 |
"legacy": null,
|
| 74 |
-
"
|
| 75 |
-
"model_max_length": 16384,
|
| 76 |
"pad_token": "<unk>",
|
| 77 |
"padding_side": "right",
|
| 78 |
-
"prefix_token": "▁<PRE>",
|
| 79 |
"sp_model_kwargs": {},
|
| 80 |
-
"suffix_token": "▁<SUF>",
|
| 81 |
"tokenizer_class": "CodeLlamaTokenizer",
|
| 82 |
"unk_token": "<unk>",
|
| 83 |
"use_default_system_prompt": false
|
|
|
|
| 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": null,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 35 |
"pad_token": "<unk>",
|
| 36 |
"padding_side": "right",
|
|
|
|
| 37 |
"sp_model_kwargs": {},
|
|
|
|
| 38 |
"tokenizer_class": "CodeLlamaTokenizer",
|
| 39 |
"unk_token": "<unk>",
|
| 40 |
"use_default_system_prompt": false
|