Commit
·
9238f6a
1
Parent(s):
11d59b7
fix: update tokenizer_config
Browse files- tokenizer_config.json +8 -8
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
| 5 |
"content": "<|endoftext|>",
|
|
@@ -9,12 +16,5 @@
|
|
| 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 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 18 |
-
"unk_token": "<|endoftext|>",
|
| 19 |
-
"pad_token": "<|endoftext|>",
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": true,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>",
|
| 6 |
+
"pad_token": "<|endoftext|>",
|
| 7 |
+
"model_max_length": 1024,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"clean_up_tokenization_spaces": true,
|
| 10 |
"added_tokens_decoder": {
|
| 11 |
"50256": {
|
| 12 |
"content": "<|endoftext|>",
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
}
|
| 19 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
}
|