gemma-2b-function-calling / tokenizer_config.json
rodrigo-pedro's picture
Upload tokenizer
848ca9d verified
raw
history blame
2.33 kB
{
"add_bos_token": true,
"add_eos_token": true,
"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": "{% for message in messages %}{% if message['from'] == 'system' %}{{ '<start_of_turn>user\\n' + message['value'] }}{% elif message['from'] == 'human' %}{% if loop.index0 == 1 %}{{ '\\nUser Question:\\n' }}{% else %}{{ '<start_of_turn>user\\n' }}{% endif %}{{ message['value'] + '<end_of_turn>' }}{% elif message['from'] == 'gpt' %}{{ '<start_of_turn>model\\n' + message['value'] + ' ' + '<end_of_turn>' }}{% elif message['from'] == 'function_response' %}{{ '<start_of_turn>user\\n' + message['value'] + ' ' + '<end_of_turn>' }}{% endif %}{% if not loop.last %}{{ '\\n' }}{% endif %}{% endfor %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if add_generation_prompt %}{{ '\\n<start_of_turn>model\\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<eos>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}