89 lines
2.4 KiB
JSON
89 lines
2.4 KiB
JSON
|
{
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"151643": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151644": {
|
||
|
|
"content": "<|im_start|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151645": {
|
||
|
|
"content": "<|im_end|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151646": {
|
||
|
|
"content": "<R>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151647": {
|
||
|
|
"content": "<S>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151648": {
|
||
|
|
"content": "<X>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151649": {
|
||
|
|
"content": "<mask>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151650": {
|
||
|
|
"content": "<sep>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151651": {
|
||
|
|
"content": "<extra_0>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<R>", "<S>", "<X>", "<mask>", "<sep>", "<extra_0>"],
|
||
|
|
"bos_token": null,
|
||
|
|
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{% if loop.last %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>'}}{% else %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{{ '<|endoftext|>' }}",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|im_end|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"model_max_length": 131072,
|
||
|
|
"pad_token": "<|endoftext|>",
|
||
|
|
"split_special_tokens": false,
|
||
|
|
"tokenizer_class": "Qwen2Tokenizer",
|
||
|
|
"unk_token": null
|
||
|
|
}
|