Update tokenizer_config.json
Browse files- tokenizer_config.json +6 -23
tokenizer_config.json
CHANGED
|
@@ -1,18 +1,17 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"100000": {
|
| 7 |
-
"content": "
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": true,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
-
|
| 15 |
-
"content": "
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": true,
|
| 18 |
"rstrip": false,
|
|
@@ -130,34 +129,18 @@
|
|
| 130 |
"rstrip": false,
|
| 131 |
"single_word": false,
|
| 132 |
"special": true
|
| 133 |
-
},
|
| 134 |
-
"bos_token": {
|
| 135 |
-
"__type": "AddedToken",
|
| 136 |
-
"content": "<|begin▁of▁sentence|>",
|
| 137 |
-
"lstrip": false,
|
| 138 |
-
"normalized": true,
|
| 139 |
-
"rstrip": false,
|
| 140 |
-
"single_word": false
|
| 141 |
-
},
|
| 142 |
-
"eos_token": {
|
| 143 |
-
"__type": "AddedToken",
|
| 144 |
-
"content": "<|end▁of▁sentence|>",
|
| 145 |
-
"lstrip": false,
|
| 146 |
-
"normalized": true,
|
| 147 |
-
"rstrip": false,
|
| 148 |
-
"single_word": false
|
| 149 |
}
|
| 150 |
},
|
| 151 |
"additional_special_tokens": [
|
| 152 |
"<image_placeholder>"
|
| 153 |
],
|
| 154 |
-
"bos_token": "
|
| 155 |
"clean_up_tokenization_spaces": false,
|
| 156 |
-
"eos_token": "
|
| 157 |
"model_max_length": 16384,
|
| 158 |
"pad_token": null,
|
| 159 |
"processor_class": "VLChatProcessor",
|
| 160 |
"tokenizer_class": "LlamaTokenizer",
|
| 161 |
"unk_token": null,
|
| 162 |
"use_default_system_prompt": false
|
| 163 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"100000": {
|
| 6 |
+
"content": "<|begin_of_sentence|>",
|
| 7 |
"lstrip": false,
|
| 8 |
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
+
"100001": {
|
| 14 |
+
"content": "<|end_of_sentence|>",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": true,
|
| 17 |
"rstrip": false,
|
|
|
|
| 129 |
"rstrip": false,
|
| 130 |
"single_word": false,
|
| 131 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
}
|
| 133 |
},
|
| 134 |
"additional_special_tokens": [
|
| 135 |
"<image_placeholder>"
|
| 136 |
],
|
| 137 |
+
"bos_token": "<|begin_of_sentence|>",
|
| 138 |
"clean_up_tokenization_spaces": false,
|
| 139 |
+
"eos_token": "<|end_of_sentence|>",
|
| 140 |
"model_max_length": 16384,
|
| 141 |
"pad_token": null,
|
| 142 |
"processor_class": "VLChatProcessor",
|
| 143 |
"tokenizer_class": "LlamaTokenizer",
|
| 144 |
"unk_token": null,
|
| 145 |
"use_default_system_prompt": false
|
| 146 |
+
}
|