19 lines
1.1 KiB
JSON
19 lines
1.1 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": 8192,
|
||
|
|
"pad_token": "<|reserved_special_token_250|>",
|
||
|
|
"padding_side": "right",
|
||
|
|
"tokenizer_class": "TokenizersBackend",
|
||
|
|
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages %}{% else %}{% set default_system = [{'role': 'system', 'content': 'You are a phonetic transcriber. Transpose only English and Denglish words into German phonetics.'}] %}{% set loop_messages = default_system + messages %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}{% if message['role'] == 'user' %}{{ '[DENGLISH]' + message['content'] | trim + '<|eot_id|>' }}{% else %}{{ message['content'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
|
||
|
|
}
|