Commit History

Upload llama-8b-v3-instruct-f16.imatrix
efea34a
verified

ggerganov commited on

imatrix : remove incompatible data as per llama.cpp/6387
25bf15c
verified

ggerganov commited on

mistral : add f16 imatrix
bb14cf8
verified

ggerganov commited on

mixtral : add iq3_s imatrix
bd8943b
verified

ggerganov commited on

grok-1 : add iq3_s imatrix
2900e11
verified

ggerganov commited on

initial commit
33f9e8a
verified

ggerganov commited on