TheBloke
/

Qwen-14B-Chat-GPTQ

Text Generation

4-bit precision

Model card Files Files and versions Community

Qwen-14B-Chat-GPTQ / tokenizer_config.json

TheBloke's picture

GPTQ model commit

114e36f 8 months ago

raw history blame

No virus

173 Bytes

	{
	"model_max_length": 8192,
	"tokenizer_class": "QWenTokenizer",
	"auto_map": {
	"AutoTokenizer": [
	"tokenization_qwen.QWenTokenizer",
	null
	]
	}
	}