beng_bpe / tokenizer_config.json
spitfire4794's picture
Update tokenizer_class to PreTrainedTokenizerFast for GGUF compatibility
5d34c66 verified
Raw
History Blame Contribute Delete
554 Bytes
{
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|tool_call|>",
"<|/tool_call|>",
"<|tool_response|>",
"<|begin_of_thought|>",
"<|end_of_thought|>",
"<|reserved_0|>",
"<|reserved_1|>"
],
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|endoftext|>"
}