maccy-106m-base / tokenizer_config.json
bgub's picture
Initial Maccy-106M release
4eb89a5 verified
Raw
History Blame Contribute Delete
447 Bytes
{
"backend": "tokenizers",
"bos_token": "<|bos|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|assistant_end|>",
"extra_special_tokens": [
"<|user_start|>",
"<|user_end|>",
"<|assistant_start|>",
"<|assistant_end|>",
"<|python_start|>",
"<|python_end|>",
"<|output_start|>",
"<|output_end|>"
],
"model_max_length": 1024,
"pad_token": "<|bos|>",
"tokenizer_class": "TokenizersBackend"
}