Upload tokenizer
Browse files- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
@@ -41,12 +41,13 @@
|
|
41 |
"<|im_end|>"
|
42 |
],
|
43 |
"bos_token": "<|endoftext|>",
|
|
|
44 |
"clean_up_tokenization_spaces": false,
|
45 |
"eos_token": "<|endoftext|>",
|
46 |
"errors": "replace",
|
47 |
"model_max_length": 512,
|
48 |
"pad_token": "<|endoftext|>",
|
49 |
"padding_side": "right",
|
50 |
-
"tokenizer_class": "
|
51 |
"unk_token": "<|endoftext|>"
|
52 |
}
|
|
|
41 |
"<|im_end|>"
|
42 |
],
|
43 |
"bos_token": "<|endoftext|>",
|
44 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named Securitron, trained by Aquilax.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
45 |
"clean_up_tokenization_spaces": false,
|
46 |
"eos_token": "<|endoftext|>",
|
47 |
"errors": "replace",
|
48 |
"model_max_length": 512,
|
49 |
"pad_token": "<|endoftext|>",
|
50 |
"padding_side": "right",
|
51 |
+
"tokenizer_class": "CustomGPT2Tokenizer",
|
52 |
"unk_token": "<|endoftext|>"
|
53 |
}
|