Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -20
tokenizer_config.json
CHANGED
@@ -1,20 +1 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"50256": {
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
}
|
12 |
-
},
|
13 |
-
"bos_token": "<|endoftext|>",
|
14 |
-
"clean_up_tokenization_spaces": true,
|
15 |
-
"eos_token": "<|endoftext|>",
|
16 |
-
"model_max_length": 1024,
|
17 |
-
"pad_token": "<|endoftext|>",
|
18 |
-
"tokenizer_class": "GPT2Tokenizer",
|
19 |
-
"unk_token": "<|endoftext|>"
|
20 |
-
}
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./models/", "tokenizer_class": "GPT2Tokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|