72 lines
2.1 KiB
JSON
72 lines
2.1 KiB
JSON
{
|
|
"add_bos_token": true,
|
|
"add_eos_token": false,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<pad>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<unk>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|begin_of_text|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"3": {
|
|
"content": "<|end_of_text|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64000": {
|
|
"content": "<|eot_id|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64001": {
|
|
"content": "<|start_header_id|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"64002": {
|
|
"content": "<|end_header_id|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
}
|
|
},
|
|
"bos_token": "<|begin_of_text|>",
|
|
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|eot_id|>",
|
|
"extra_special_tokens": {},
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "<pad>",
|
|
"tokenizer_class": "PreTrainedTokenizer",
|
|
"unk_token": "<unk>"
|
|
}
|