mambaoutai / tokenizer_config.json
cthiriet's picture
Add model
cf86e12
{
"added_tokens_decoder": {
"0": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<start_system>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<start_user>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<start_assistant>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<end_message>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<start_user>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'system' %}{{ '<start_system>' + message['content'].strip() + '<end_message>' }}{% elif message['role'] == 'assistant' %}{{ '<start_assistant>' + message['content'] + '<end_message>' }}{% else %}{{ raise_exception('Only system, user and assistant roles are supported.') }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<start_assistant>' }}{% endif %}{% endfor %}",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "PreTrainedTokenizerFast"
}