Commit
•
390a3ad
1
Parent(s):
6d03aea
Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer.json +0 -0
- tokenizer_config.json +4 -28
- vocab.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"unk_token": {
|
| 17 |
-
"content": "<|endoftext|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": true,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,33 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"bos_token":
|
| 5 |
-
"__type": "AddedToken",
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
"clean_up_tokenization_spaces": true,
|
| 13 |
-
"eos_token":
|
| 14 |
-
|
| 15 |
-
"content": "<|endoftext|>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": true,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
-
"errors": "replace",
|
| 22 |
-
"model_max_length": 2048,
|
| 23 |
-
"pad_token": null,
|
| 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_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1024,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|