63 lines
1.6 KiB
JSON
63 lines
1.6 KiB
JSON
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<|im_start|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"2": {
|
||
|
|
"content": "<|im_end|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"3": {
|
||
|
|
"content": "<|fim_prefix|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"4": {
|
||
|
|
"content": "<|fim_middle|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"5": {
|
||
|
|
"content": "<|fim_suffix|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"model_max_length": 2048,
|
||
|
|
"pad_token": "<|endoftext|>",
|
||
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
||
|
|
"unk_token": null,
|
||
|
|
"chat_template": "{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
||
|
|
}
|