From 656190750d91740d468eafcbe3b53f7fd3d1c780 Mon Sep 17 00:00:00 2001 From: Andrei Betlen Date: Tue, 25 Apr 2023 19:03:41 -0400 Subject: [PATCH] Update llama.cpp --- examples/llama_cpp.py | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/llama_cpp.py b/examples/llama_cpp.py index 90f498aa5..7c2254015 100644 --- a/examples/llama_cpp.py +++ b/examples/llama_cpp.py @@ -119,6 +119,7 @@ LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = ctypes.c_int( ) # tok_embeddings.weight and output.weight are F16 LLAMA_FTYPE_MOSTLY_Q4_2 = ctypes.c_int(5) # except 1d tensors LLAMA_FTYPE_MOSTLY_Q4_3 = ctypes.c_int(6) # except 1d tensors +LLAMA_FTYPE_MOSTLY_Q8_0 = ctypes.c_int(7) # except 1d tensors # Functions