Paul Weber
commited on
Commit
·
0a5ebd5
1
Parent(s):
18151ff
Added config
Browse files- tokenizer_config.json +26 -0
tokenizer_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|endoftext|>",
|
14 |
+
"errors": "replace",
|
15 |
+
"model_max_length": 2048,
|
16 |
+
"pad_token": null,
|
17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
18 |
+
"unk_token": {
|
19 |
+
"__type": "AddedToken",
|
20 |
+
"content": "<|endoftext|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
}
|
26 |
+
}
|