CCRss
/

Llama-3.1-Nemotron-70B-Instruct-HF-calib-data-kk-akylbek_AWQ-4bit-g128-gemm

4-bit precision

Model card Files Files and versions Community

Llama-3.1-Nemotron-70B-Instruct-HF-calib-data-kk-akylbek_AWQ-4bit-g128-gemm / README.md

CCRss's picture

Update README.md

5cad553 verified 3 months ago

|

history blame contribute delete

128 Bytes

	kk + mix Akylbek data
	quant_config = {
	"zero_point": True,
	"q_group_size": 128,
	"w_bit": 4,
	"version": "GEMM"
	}