quantize_config.json · study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4 at main

Qwen1.5-110B-Chat-GPTQ-Int4 / quantize_config.json

Jintao Huang

first commit

5afcf65 about 2 months ago

No virus

243 Bytes

	{
	"bits": 4,
	"dataset": "sharegpt-gpt4-mini,alpaca-zh,alpaca-en",
	"group_size": 128,
	"damp_percent": 0.1,
	"desc_act": false,
	"sym": true,
	"true_sequential": true,
	"quant_method": "gptq",
	"modules_in_block_to_quantize": null
	}