tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
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": 1000000000000000019884624838656,
|
19 |
+
"pad_token": null,
|
20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
21 |
+
"unk_token": "<|endoftext|>"
|
22 |
+
}
|