cr-model-v1 / tokenizer_config.json
TwT-6's picture
Upload 11 files
0e2ce9c verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|omni_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|omni_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|omni_start|>",
"<|omni_end|>"
],
"bos_token": "<|omni_start|>",
"chat_template": "{% for message in messages %}{{'<|omni_start|>' + message['role'] + '\n' + message['content'] + '<|omni_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|omni_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 4096,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}