zohaib99k
/

Nous-Hermes-Llama2-8bit-GPTQ

Text Generation

synthetic instruction

text-generation-inference

Model card Files Files and versions Community

Nous-Hermes-Llama2-8bit-GPTQ / quantize_config.json

zohaib99k's picture

Upload 13 files

7483809 10 months ago

raw history blame contribute delete

No virus

184 Bytes

	{
	"bits": 8,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": true,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": null
	}