Commit
•
714dd05
1
Parent(s):
186e517
Upload tokenizer
Browse files- special_tokens_map.json +3 -4
- tokenizer_config.json +4 -3
special_tokens_map.json
CHANGED
|
@@ -2,22 +2,21 @@
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "<unk>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
| 20 |
-
"normalized":
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
}
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
tokenizer_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
@@ -14,20 +14,21 @@
|
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
| 16 |
"lstrip": false,
|
| 17 |
-
"normalized":
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"legacy": false,
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": null,
|
|
|
|
| 24 |
"sp_model_kwargs": {},
|
| 25 |
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|
| 28 |
"content": "<unk>",
|
| 29 |
"lstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false
|
| 33 |
}
|
|
|
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
| 16 |
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"legacy": false,
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
"sp_model_kwargs": {},
|
| 26 |
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
"unk_token": {
|
| 28 |
"__type": "AddedToken",
|
| 29 |
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
}
|