TriusLD / tokenizer_config.json
bctnry's picture
TriusLD: 64,972-token multilingual byte-level BPE
6070dfa verified
Raw History Blame Contribute Delete
482 Bytes
{
"backend": "tokenizers",
"bos_token": "<|bos|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|eos|>",
"extra_special_tokens": [
"<|system|>",
"<|user|>",
"<|assistant|>",
"<|end|>",
"<|fim_prefix|>",
"<|fim_middle|>",
"<|fim_suffix|>",
"<|tool_call|>",
"<|tool_result|>",
"<|image|>"
],
"model_max_length": 131072,
"pad_token": "<|pad|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|unk|>"
}