dranger003

/

c4ai-command-r-plus-iMat.GGUF

like 132

I built llama.cpp in ollama from the branch in the PR, yet whenever I load the IQ4_KM gguf file I get the "invalid file magic" error. Does what I have here look right for ollama on Windows 11?

PS C:\Users\Justin\Workspace\ollama> cd .\llm\llama.cpp\
PS C:\Users\Justin\Workspace\ollama\llm\llama.cpp> git status
HEAD detached at ea1aeba4
nothing to commit, working tree clean
PS C:\Users\Justin\Workspace\ollama\llm\llama.cpp> cd ..
PS C:\Users\Justin\Workspace\ollama\llm> cd ..
PS C:\Users\Justin\Workspace\ollama> $env:CGO_ENABLED="1"
PS C:\Users\Justin\Workspace\ollama> go generate ./...
Submodule path '../llama.cpp': checked out 'ea1aeba48b42f5f6ec41412ef271f5d708b0fa2f'
Updated 0 paths from the index
Checking for MinGW...

CommandType     Name                                               Version    Source
-----------     ----                                               -------    ------
Application     gcc.exe                                            0.0.0.0    C:\ProgramData\mingw64\mingw64\bin\gcc.exe
Application     mingw32-make.exe                                   0.0.0.0    C:\ProgramData\mingw64\mingw64\bin\mingw32-make.exe
Building static library
...
Generating build details from Git
  -- Found Git: C:/Program Files/Git/cmd/git.exe (found version "2.44.0.windows.1")
  build_info.vcxproj -> C:\Users\Justin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\common\build_info.dir\Release\build_info.lib
  ggml.vcxproj -> C:\Users\Justin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\ggml.dir\Release\ggml.lib
  llama.cpp
C:\Users\Justin\Workspace\ollama\llm\llama.cpp\llama.cpp(14181,9): warning C4297: 'llama_load_model_from_file': function assumed not to throw an exception but does [C:\Users\Jus
tin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\llama.vcxproj]
  C:\Users\Justin\Workspace\ollama\llm\llama.cpp\llama.cpp(14181,9):
  __declspec(nothrow), throw(), noexcept(true), or noexcept was specified on the function

  Auto build dll exports
     Creating library C:/Users/Justin/Workspace/ollama/llm/build/windows/amd64/cuda_v12.3/Release/llama.lib and object C:/Users/Justin/Workspace/ollama/llm/build/windows/amd64/c
  uda_v12.3/Release/llama.exp
  llama.vcxproj -> C:\Users\Justin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\bin\Release\llama.dll
  llava.vcxproj -> C:\Users\Justin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\examples\llava\llava.dir\Release\llava.lib
  common.vcxproj -> C:\Users\Justin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\common\Release\common.lib
     Creating library C:/Users/Justin/Workspace/ollama/llm/build/windows/amd64/cuda_v12.3/ext_server/Release/ollama_llama_server.lib and object C:/Users/Justin/Workspace/ollama/
  llm/build/windows/amd64/cuda_v12.3/ext_server/Release/ollama_llama_server.exp
  ollama_llama_server.vcxproj -> C:\Users\Justin\Workspace\ollama\llm\build\windows\amd64\cuda_v12.3\bin\Release\ollama_llama_server.exe
gzip not installed, not compressing files
Updated 1 path from the index
Updated 1 path from the index

go generate completed.  LLM runners: cpu cpu_avx cpu_avx2 cuda_v12.3 cuda_v12.4
PS C:\Users\Justin\Workspace\ollama> go build .

PS C:\Users\Justin\Workspace\ollama> .\ollama.exe serve
time=2024-04-08T19:24:05.373-05:00 level=INFO source=images.go:793 msg="total blobs: 53"
time=2024-04-08T19:24:06.287-05:00 level=INFO source=images.go:800 msg="total unused blobs removed: 2"
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
 - using env:   export GIN_MODE=release
 - using code:  gin.SetMode(gin.ReleaseMode)

[GIN-debug] POST   /api/pull                 --> github.com/ollama/ollama/server.PullModelHandler (5 handlers)
[GIN-debug] POST   /api/generate             --> github.com/ollama/ollama/server.GenerateHandler (5 handlers)
[GIN-debug] POST   /api/chat                 --> github.com/ollama/ollama/server.ChatHandler (5 handlers)
[GIN-debug] POST   /api/embeddings           --> github.com/ollama/ollama/server.EmbeddingsHandler (5 handlers)
[GIN-debug] POST   /api/create               --> github.com/ollama/ollama/server.CreateModelHandler (5 handlers)
[GIN-debug] POST   /api/push                 --> github.com/ollama/ollama/server.PushModelHandler (5 handlers)
[GIN-debug] POST   /api/copy                 --> github.com/ollama/ollama/server.CopyModelHandler (5 handlers)
[GIN-debug] DELETE /api/delete               --> github.com/ollama/ollama/server.DeleteModelHandler (5 handlers)
[GIN-debug] POST   /api/show                 --> github.com/ollama/ollama/server.ShowModelHandler (5 handlers)
[GIN-debug] POST   /api/blobs/:digest        --> github.com/ollama/ollama/server.CreateBlobHandler (5 handlers)
[GIN-debug] HEAD   /api/blobs/:digest        --> github.com/ollama/ollama/server.HeadBlobHandler (5 handlers)
[GIN-debug] POST   /v1/chat/completions      --> github.com/ollama/ollama/server.ChatHandler (6 handlers)
[GIN-debug] GET    /                         --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] GET    /api/tags                 --> github.com/ollama/ollama/server.ListModelsHandler (5 handlers)
[GIN-debug] GET    /api/version              --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
[GIN-debug] HEAD   /                         --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] HEAD   /api/tags                 --> github.com/ollama/ollama/server.ListModelsHandler (5 handlers)
[GIN-debug] HEAD   /api/version              --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
time=2024-04-08T19:24:06.288-05:00 level=INFO source=routes.go:1121 msg="Listening on [::]:11434 (version 0.0.0)"
time=2024-04-08T19:24:06.298-05:00 level=INFO source=payload.go:28 msg="extracting embedded files" dir=C:\Users\Justin\AppData\Local\Temp\ollama4257825441\runners
time=2024-04-08T19:24:06.329-05:00 level=INFO source=payload.go:41 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v12.3]"

PS C:\Users\Justin\Workspace\ollama> .\ollama.exe create commandrplus -f C:\Users\Justin\Downloads\ModelFile
transferring model data
creating model layer
Error: invalid file magic