ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V6 / tokenizer_config.json
allen0909's picture
Training in progress, step 100
4890632 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% if messages[0]['role'] == 'system' %}\n {% set loop_messages = messages[1:] %}\n {% set system_message = messages[0]['content'] %}\n{% else %}\n {% set loop_messages = messages %}\n {% set system_message = false %}\n{% endif %}\n{% for message in loop_messages %}\n {% if loop.index0 == 0 and system_message != false %}\n {% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}\n {% else %}\n {% set content = message['content'] %}\n {% endif %}\n {% if message['role'] == 'user' %}\n {{- bos_token + '[INST] ' + content.strip() + ' [/INST]' -}}\n {% elif message['role'] == 'system' %}\n {{- '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' -}}\n {% elif message['role'] == 'assistant' %}\n {{- ' ' + content.strip() + ' ' + eos_token -}}\n {% endif %}\n{% endfor %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 2048,
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}