bloom-3b-conversational / tokenizer_config.json
CreitinGameplays's picture
Update tokenizer_config.json
56d3e3e verified
raw
history blame
2.09 kB
{
"add_eos_token": true,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250680": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250681": {
"content": "<|prompter|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250682": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|system|>",
"<|prompter|>",
"<|assistant|>"
],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|prompter|>' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "left",
"tokenizer_class": "BloomTokenizer",
"unk_token": "<unk>"
}