Commit
•
7daaafb
1
Parent(s):
a927eb9
Upload tokenizer
Browse files- tokenizer_config.json +13 -24
tokenizer_config.json
CHANGED
|
@@ -1,33 +1,22 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
| 11 |
},
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": true,
|
| 13 |
-
"eos_token":
|
| 14 |
-
"__type": "AddedToken",
|
| 15 |
-
"content": "<|endoftext|>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": true,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
"errors": "replace",
|
| 22 |
"model_max_length": 1024,
|
| 23 |
-
"pad_token":
|
| 24 |
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
-
"unk_token":
|
| 26 |
-
"__type": "AddedToken",
|
| 27 |
-
"content": "<|endoftext|>",
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": true,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
}
|
| 33 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"errors": "replace",
|
| 18 |
"model_max_length": 1024,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
}
|