idk wth is happening help

[Kilgorio]

PS C:\Users\Admin> cd D:\Software\GPT4ALL\llama.cpp PS D:\Software\GPT4ALL\llama.cpp> make process_begin: CreateProcess(NULL, uname -s, ...) failed. Makefile:2: pipe: No error process_begin: CreateProcess(NULL, uname -p, ...) failed. Makefile:6: pipe: No error process_begin: CreateProcess(NULL, uname -m, ...) failed. Makefile:10: pipe: No error 'cc' is not recognized as an internal or external command, operable program or batch file. 'head' is not recognized as an internal or external command, operable program or batch file. I llama.cpp build info: I UNAME_S: I UNAME_P: I UNAME_M: I CFLAGS: -I. -O3 -DNDEBUG -std=c11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function -mfma -mf16c -mavx -mavx2 I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function I LDFLAGS: I CC: I CXX:

cc -I. -O3 -DNDEBUG -std=c11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function -mfma -mf16c -mavx -mavx2 -c ggml.c -o ggml.o process_begin: CreateProcess(NULL, cc -I. -O3 -DNDEBUG -std=c11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function -mfma -mf16c -mavx -mavx2 -c ggml.c -o ggml.o, ...) failed. make (e=2): The system cannot find the file specified. make: *** [Makefile:229: ggml.o] Error 2

[MillionthOdin16]

This is definitely not proper format. Look at the issue template, look at other issues, put in effort to explaining your issue before expecting others to pick up your lack.

[Kilgorio]

I looked at it and I said

"I don't have time for that"

[slaren]

You need to use cmake to build on windows.

[Kilgorio]

but how

[Kilgorio]

I am only doing this to get tokenizer.model so I can convert gpt4all so it can work with kobold ai and with that it can work with tavernAI I think I will get tokenizer.model trough this cause currently I don't have it

[slaren]

The tokenizer.model file is part of the original llama models distribution and you won't get that by compiling this project. We should include build instructions for windows in the README, but for now you can use one of the pre-compiled binaries available at https://github.com/ggerganov/llama.cpp/tags

[Kilgorio]

I still can't find it

[slaren]

@Kilgorio unfortunately I cannot tell you where to find the original llama models as that is explicitly against the policy of this project. You will have to look for that elsewhere.