Upload tokenizer
Browse files- added_tokens.json +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -27
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50257
|
3 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,35 +1,11 @@
|
|
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 |
-
"__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": 1000000000000000019884624838656,
|
23 |
-
"pad_token": null,
|
24 |
"pad_token_id": 50256,
|
25 |
"padding_side": "right",
|
26 |
"tokenizer_class": "GPT2Tokenizer",
|
27 |
-
"unk_token":
|
28 |
-
"__type": "AddedToken",
|
29 |
-
"content": "<|endoftext|>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false
|
34 |
-
}
|
35 |
}
|
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
7 |
"pad_token_id": 50256,
|
8 |
"padding_side": "right",
|
9 |
"tokenizer_class": "GPT2Tokenizer",
|
10 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|