Commit ·
dc1056a
1
Parent(s): 9f55c75
Update tokenizer_config.json
Browse files- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
|
@@ -123,7 +123,8 @@
|
|
| 123 |
"<|user|>", "<|assistant|>", "<|observation|>", "<|begin_of_image|>", "<|end_of_image|>",
|
| 124 |
"<|begin_of_video|>", "<|end_of_video|>"],
|
| 125 |
"clean_up_tokenization_spaces": false,
|
| 126 |
-
"chat_template": "[gMASK]<sop>{% for item in messages %}{% if item['content'] %}<|{{ item['role'] }}|>{{ item['metadata'] }}\n{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}",
|
|
|
|
| 127 |
"eos_token": "<|endoftext|>",
|
| 128 |
"pad_token": "<|endoftext|>",
|
| 129 |
"model_max_length": 1024000,
|
|
|
|
| 123 |
"<|user|>", "<|assistant|>", "<|observation|>", "<|begin_of_image|>", "<|end_of_image|>",
|
| 124 |
"<|begin_of_video|>", "<|end_of_video|>"],
|
| 125 |
"clean_up_tokenization_spaces": false,
|
| 126 |
+
"chat_template": "[gMASK]<sop>{% for item in messages %}{% if item['content'] %}<|{{ item['role'] }}|>{{ item['metadata'] }}\n{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}",
|
| 127 |
+
"do_lower_case": false,
|
| 128 |
"eos_token": "<|endoftext|>",
|
| 129 |
"pad_token": "<|endoftext|>",
|
| 130 |
"model_max_length": 1024000,
|