RachidAR
/

WizardLM-7B-q6_K-ggml

Model card Files Files and versions Community

WizardLM-7B-q6_K-ggml / README.md

RachidAR's picture

Update README.md

fc71d38 about 1 year ago

|

history blame contribute delete

110 Bytes

	Works with latest llama.cpp version. (05/06/23 build = 622)

	F16 perplexity : 5.9066

	q6_K perplexity : 5.9110