falcon-7b-instruct / tokenizer_config.json
nilabhra's picture
add chat template to tokenizer_config.json (#111)
0b9684d verified
raw
history blame
1.13 kB
{
"add_prefix_space": false,
"eos_token": "<|endoftext|>",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 2048,
"name_or_path": "tiiuae/falcon_tokenizer",
"special_tokens_map_file": null,
"tokenizer_class": "PreTrainedTokenizerFast",
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{{ system_message.strip() }}{% endif %}{% if message['role'] == 'user' %}{{ '\n\nUser: ' + message['content'].strip().replace('\r\n', '\n').replace('\n\n', '\n') }}{% elif message['role'] == 'assistant' %}{{ '\n\nAssistant: ' + message['content'].strip().replace('\r\n', '\n').replace('\n\n', '\n') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\nAssistant:' }}{% endif %}"
}