19 lines
1.6 KiB
JSON
19 lines
1.6 KiB
JSON
|
{
|
||
|
|
"backend": "tokenizers",
|
||
|
|
"bos_token": "<|begin_of_text|>",
|
||
|
|
"clean_up_tokenization_spaces": true,
|
||
|
|
"eos_token": "<|eot_id|>",
|
||
|
|
"from_slow": true,
|
||
|
|
"is_local": false,
|
||
|
|
"legacy": false,
|
||
|
|
"model_input_names": [
|
||
|
|
"input_ids",
|
||
|
|
"attention_mask"
|
||
|
|
],
|
||
|
|
"model_max_length": 131072,
|
||
|
|
"pad_token": "<|finetune_right_pad_id|>",
|
||
|
|
"padding_side": "left",
|
||
|
|
"tokenizer_class": "TokenizersBackend",
|
||
|
|
"unk_token": null,
|
||
|
|
"chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% elif message['role'] == 'assistant' %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% elif message['from'] == 'gpt' %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['from'] + '<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% endif %}"
|
||
|
|
}
|