Open kallewoof opened 1 year ago
I suspect this issue is related to issue #1186, and is solved by updating llama.cpp. According to https://github.com/ggerganov/whisper.cpp/commits/master/examples/talk-llama/llama.cpp, llama.cpp has been updated several times since you reported this issue. Perhaps it is already solved?
This
is from
https://github.com/ggerganov/whisper.cpp/blob/4774d2feb01a772a15de81ffc34b34a1f294f020/examples/talk-llama/llama.cpp#L488-L498
despite me using type
3
above in./quantize
call. Type14
isQ4_K_S
.If I use a
q5_k_m
model it complains about tensor type 13, despiteQ5_K_M
actually being 17, so I think there is a file format issue going on.Probably unrelated: I had to manually modify the
c++
line (MacBook Pro M1 16 inch on Ventura) fortalk-llama
to(i.e. I added
-lobjc -framework Cocoa -framework CoreML whisper-encoder.o whisper-encoder-impl.o
) in order for it to compile without linker issues. As I said, I don't think that is related to the above issue though.