Commit
•
b1d9ada
1
Parent(s):
2db415d
Upload tokenizer
Browse files- added_tokens.json +0 -1
- special_tokens_map.json +3 -3
- tokenizer.json +0 -9
- tokenizer_config.json +3 -11
added_tokens.json
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
"</s>": 5,
|
| 3 |
"<s>": 4,
|
| 4 |
"<unk>": 3,
|
| 5 |
-
"<|endoftext|>": 25000,
|
| 6 |
"<|im_begin|>": 0,
|
| 7 |
"<|im_end|>": 1,
|
| 8 |
"[PAD]": 2
|
|
|
|
| 2 |
"</s>": 5,
|
| 3 |
"<s>": 4,
|
| 4 |
"<unk>": 3,
|
|
|
|
| 5 |
"<|im_begin|>": 0,
|
| 6 |
"<|im_end|>": 1,
|
| 7 |
"[PAD]": 2
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "
|
| 3 |
-
"eos_token": "
|
| 4 |
-
"unk_token": "
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
}
|
tokenizer.json
CHANGED
|
@@ -56,15 +56,6 @@
|
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
"special": true
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"id": 25000,
|
| 62 |
-
"content": "<|endoftext|>",
|
| 63 |
-
"single_word": false,
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"normalized": false,
|
| 67 |
-
"special": true
|
| 68 |
}
|
| 69 |
],
|
| 70 |
"normalizer": null,
|
|
|
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -48,21 +48,13 @@
|
|
| 48 |
"rstrip": false,
|
| 49 |
"single_word": false,
|
| 50 |
"special": true
|
| 51 |
-
},
|
| 52 |
-
"25000": {
|
| 53 |
-
"content": "<|endoftext|>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
}
|
| 60 |
},
|
| 61 |
"additional_special_tokens": [],
|
| 62 |
-
"bos_token": "
|
| 63 |
"clean_up_tokenization_spaces": true,
|
| 64 |
-
"eos_token": "
|
| 65 |
"model_max_length": 1000000000000000019884624838656,
|
| 66 |
"tokenizer_class": "GPT2Tokenizer",
|
| 67 |
-
"unk_token": "
|
| 68 |
}
|
|
|
|
| 48 |
"rstrip": false,
|
| 49 |
"single_word": false,
|
| 50 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
}
|
| 52 |
},
|
| 53 |
"additional_special_tokens": [],
|
| 54 |
+
"bos_token": "<s>",
|
| 55 |
"clean_up_tokenization_spaces": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
"model_max_length": 1000000000000000019884624838656,
|
| 58 |
"tokenizer_class": "GPT2Tokenizer",
|
| 59 |
+
"unk_token": "<unk>"
|
| 60 |
}
|