|
--- |
|
license: llama2 |
|
--- |
|
This a custom built Mistral Llama.cpp model. |
|
|
|
https://github.com/Deadsg/Bat-.-LLama-.-CPP |
|
|
|
Here is the docs for further referencing: |
|
|
|
https://github.com/mpwang/llama-cpp-windows-guide |
|
|
|
https://github.com/ggerganov/llama.cpp/blob/master/README.md |
|
|
|
https://github.com/jmorganca/ollama/blob/main/docs/development.md |
|
|
|
You'll have to reform the Cmakefiles and cmakecache for your own systems. You can do this easily by setting the corrects paths for your compilers in your main Cmakelist.txt file. |
|
I'm uplaoding for ease of file reference and correct bulding reference. If you can compile the file as is, that's great. But I highly doubt it. |
|
I'm still pretty new to Coding bt if i can figure it out so can you. |
|
|
|
To properly build and make the cmake files and necessary .exe files, You'll need WSL2 and the Windows64Devkit (W64DevKit). |
|
|
|
https://github.com/skeeto/w64devkit/releases |
|
|
|
IF there's any issues or questions just submit an issue or fork and make a pull request. |
|
|
|
Will be working on a very thorough Windows guide soon. |
|
|
