code-llama-7b-text-to-sql / tokenizer_config.json
torphix's picture
Training in progress, epoch 0
bee4306 verified
raw
history blame
861 Bytes
{
"added_tokens_decoder": {},
"auto_map": {
"AutoTokenizer": [
"stabilityai/stablelm-2-zephyr-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
null
]
},
"bos_token": "<|endoftext|>",
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"tokenizer_class": "Arcade100kTokenizer"
}