Update tokenizer_config.json
Browse files- tokenizer_config.json +5 -5
tokenizer_config.json
CHANGED
|
@@ -9,15 +9,15 @@
|
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
-
"
|
| 13 |
-
"content": "
|
| 14 |
"lstrip": false,
|
| 15 |
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
-
"
|
| 21 |
"content": "<image>",
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": false,
|
|
@@ -29,11 +29,11 @@
|
|
| 29 |
"additional_special_tokens": [
|
| 30 |
"<image>"
|
| 31 |
],
|
| 32 |
-
"bos_token": "
|
| 33 |
"clean_up_tokenization_spaces": true,
|
| 34 |
"eos_token": "<|endoftext|>",
|
| 35 |
"model_max_length": 1024,
|
| 36 |
-
"pad_token": "
|
| 37 |
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
"unk_token": "<|endoftext|>"
|
| 39 |
}
|
|
|
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
+
"50256": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
"lstrip": false,
|
| 15 |
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
+
"50257": {
|
| 21 |
"content": "<image>",
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": false,
|
|
|
|
| 29 |
"additional_special_tokens": [
|
| 30 |
"<image>"
|
| 31 |
],
|
| 32 |
+
"bos_token": "<|endoftext|>",
|
| 33 |
"clean_up_tokenization_spaces": true,
|
| 34 |
"eos_token": "<|endoftext|>",
|
| 35 |
"model_max_length": 1024,
|
| 36 |
+
"pad_token": "<|endoftext|>",
|
| 37 |
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
"unk_token": "<|endoftext|>"
|
| 39 |
}
|