mpt-7b-8k-chat-gptq / tokenizer_config.json
casperhansen's picture
GPTQ quantized MPT model
081aec9
raw
history blame contribute delete
237 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 8192,
"tokenizer_class": "GPTNeoXTokenizer",
"unk_token": "<|endoftext|>"
}