Upload tokenizer
Browse files- tokenizer.json +1 -1
- tokenizer_config.json +11 -0
tokenizer.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
"single_word": false,
|
15 |
"lstrip": false,
|
16 |
"rstrip": false,
|
17 |
-
"normalized":
|
18 |
"special": true
|
19 |
}
|
20 |
],
|
|
|
14 |
"single_word": false,
|
15 |
"lstrip": false,
|
16 |
"rstrip": false,
|
17 |
+
"normalized": true,
|
18 |
"special": true
|
19 |
}
|
20 |
],
|
tokenizer_config.json
CHANGED
@@ -1,9 +1,20 @@
|
|
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 |
}
|
|
|
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 |
}
|