|
{ |
|
"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": "<eos>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"2": { |
|
"content": "<bos>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"3": { |
|
"content": "<unk>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"106": { |
|
"content": "<start_of_turn>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"107": { |
|
"content": "<end_of_turn>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"additional_special_tokens": [ |
|
"<start_of_turn>", |
|
"<end_of_turn>" |
|
], |
|
"bos_token": "<bos>", |
|
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "<eos>", |
|
"legacy": null, |
|
"max_length": 2048, |
|
"model_max_length": 2048, |
|
"pad_token": "<eos>", |
|
"sp_model_kwargs": {}, |
|
"spaces_between_special_tokens": false, |
|
"stride": 0, |
|
"tokenizer_class": "GemmaTokenizer", |
|
"truncation_side": "left", |
|
"truncation_strategy": "longest_first", |
|
"unk_token": "<unk>", |
|
"use_default_system_prompt": false |
|
} |
|
|