Upload tokenizer
Browse files- tokenizer_config.json +7 -9
tokenizer_config.json
CHANGED
|
@@ -60,6 +60,10 @@
|
|
| 60 |
}
|
| 61 |
},
|
| 62 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
"▁<PRE>",
|
| 64 |
"▁<MID>",
|
| 65 |
"▁<SUF>",
|
|
@@ -87,18 +91,12 @@
|
|
| 87 |
"legacy": null,
|
| 88 |
"middle_token": "▁<MID>",
|
| 89 |
"model_max_length": 4096,
|
| 90 |
-
"pad_token":
|
| 91 |
-
"__type": "AddedToken",
|
| 92 |
-
"content": "</s>",
|
| 93 |
-
"lstrip": false,
|
| 94 |
-
"normalized": true,
|
| 95 |
-
"rstrip": false,
|
| 96 |
-
"single_word": false
|
| 97 |
-
},
|
| 98 |
"prefix_token": "▁<PRE>",
|
| 99 |
"sp_model_kwargs": {},
|
|
|
|
| 100 |
"suffix_token": "▁<SUF>",
|
| 101 |
-
"tokenizer_class": "
|
| 102 |
"unk_token": {
|
| 103 |
"__type": "AddedToken",
|
| 104 |
"content": "<unk>",
|
|
|
|
| 60 |
}
|
| 61 |
},
|
| 62 |
"additional_special_tokens": [
|
| 63 |
+
"▁<PRE>",
|
| 64 |
+
"▁<MID>",
|
| 65 |
+
"▁<SUF>",
|
| 66 |
+
"▁<EOT>",
|
| 67 |
"▁<PRE>",
|
| 68 |
"▁<MID>",
|
| 69 |
"▁<SUF>",
|
|
|
|
| 91 |
"legacy": null,
|
| 92 |
"middle_token": "▁<MID>",
|
| 93 |
"model_max_length": 4096,
|
| 94 |
+
"pad_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
"prefix_token": "▁<PRE>",
|
| 96 |
"sp_model_kwargs": {},
|
| 97 |
+
"suffix_first": false,
|
| 98 |
"suffix_token": "▁<SUF>",
|
| 99 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
| 100 |
"unk_token": {
|
| 101 |
"__type": "AddedToken",
|
| 102 |
"content": "<unk>",
|