17 lines
801 B
JSON
17 lines
801 B
JSON
|
{
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"backend": "tokenizers",
|
||
|
|
"bos_token": "<|im_start|>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|im_end|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"extra_special_tokens": [],
|
||
|
|
"is_local": false,
|
||
|
|
"model_max_length": 8192,
|
||
|
|
"pad_token": "<|PAD_TOKEN|>",
|
||
|
|
"padding_side": "left",
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"unk_token": "�",
|
||
|
|
"vocab_size": 49152,
|
||
|
|
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
||
|
|
}
|