Qwen-14B-Chat-GPTQ / tokenizer_config.json
TheBloke's picture
GPTQ model commit
cc23038
raw
history blame
173 Bytes
{
"model_max_length": 8192,
"tokenizer_class": "QWenTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_qwen.QWenTokenizer",
null
]
}
}