Find a file
Concedo 559a1967f7 Backwards compatibility formats all done
Merge branch 'master' into concedo

# Conflicts:
#	CMakeLists.txt
#	README.md
#	llama.cpp
2023-03-31 19:01:33 +08:00
.github/ISSUE_TEMPLATE ci : re-enable AVX512 testing (Windows-MSVC) (#584) 2023-03-29 23:44:39 +03:00
examples Fix ggml_init_params in quantize 2023-03-30 12:28:25 -07:00
models Make loading weights 10-100x faster 2023-03-30 12:28:25 -07:00
prompts add example of re-act pattern (#583) 2023-03-29 10:10:24 -05:00
spm-headers deploy : add a Package.swift for SwiftPM support (#393) 2023-03-28 19:39:01 +03:00
tests tests : free llama context at the end of the test 2023-03-28 19:51:55 +03:00
.gitignore Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
cblas.h integrated libopenblas for greatly accelerated prompt processing. Windows binaries are included - feel free to build your own or to build for other platforms, but that is beyond the scope of this repo. Will fall back to non-blas if libopenblas is removed. 2023-03-30 00:43:52 +08:00
convert-ggml-to-pth.py Make loading weights 10-100x faster 2023-03-30 12:28:25 -07:00
convert-gpt4all-to-ggml.py py : add GPT4All conversion script 2023-03-29 19:29:52 +03:00
convert-gptq-to-ggml.py Make loading weights 10-100x faster 2023-03-30 12:28:25 -07:00
convert-pth-to-ggml.py Introduce GGML migration tool for new file format 2023-03-30 12:28:25 -07:00
convert-unversioned-ggml-to-ggml.py py : add GPT4All conversion script 2023-03-29 19:29:52 +03:00
expose.cpp Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
extra.cpp Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
extra.h Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
ggml.c Ensure --mlock works properly with mmap() support 2023-03-30 12:28:25 -07:00
ggml.h Ensure --mlock works properly with mmap() support 2023-03-30 12:28:25 -07:00
klite.embd Merged PR with a few changes: 2023-03-29 20:38:57 +08:00
libopenblas.dll integrated libopenblas for greatly accelerated prompt processing. Windows binaries are included - feel free to build your own or to build for other platforms, but that is beyond the scope of this repo. Will fall back to non-blas if libopenblas is removed. 2023-03-30 00:43:52 +08:00
libopenblas.lib integrated libopenblas for greatly accelerated prompt processing. Windows binaries are included - feel free to build your own or to build for other platforms, but that is beyond the scope of this repo. Will fall back to non-blas if libopenblas is removed. 2023-03-30 00:43:52 +08:00
LICENSE.md update license, added backwards compatibility with both ggml model formats, fixed context length issues. 2023-03-20 23:43:35 +08:00
llama.cpp Introduce GGML migration tool for new file format 2023-03-30 12:28:25 -07:00
llama.h Make loading weights 10-100x faster 2023-03-30 12:28:25 -07:00
llamacpp.dll Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
llamacpp_blas.dll Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
llamacpp_for_kobold.py improved console info, fixed utf encoding bugs 2023-03-31 15:38:38 +08:00
main.exe Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
make_pyinstaller.bat renamed main python script 2023-03-30 00:48:44 +08:00
Makefile Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
migrate-ggml-2023-03-30-pr613.py Introduce GGML migration tool for new file format 2023-03-30 12:28:25 -07:00
MIT_LICENSE_GGML_LLAMACPP_ONLY update license, added backwards compatibility with both ggml model formats, fixed context length issues. 2023-03-20 23:43:35 +08:00
niko.ico added a GUI for selection of models if none was passed in through command line. 2023-03-24 22:03:57 +08:00
openblas_config.h integrated libopenblas for greatly accelerated prompt processing. Windows binaries are included - feel free to build your own or to build for other platforms, but that is beyond the scope of this repo. Will fall back to non-blas if libopenblas is removed. 2023-03-30 00:43:52 +08:00
Package.swift deploy : add a Package.swift for SwiftPM support (#393) 2023-03-28 19:39:01 +03:00
preview.png resize image 2023-03-22 16:21:40 +08:00
quantize.exe Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
README.md Backwards compatibility formats all done 2023-03-31 19:01:33 +08:00
SHA256SUMS Revert "Delete SHA256SUMS for now" (#429) 2023-03-23 15:15:48 +01:00

llamacpp-for-kobold

A self contained distributable from Concedo that exposes llama.cpp function bindings, allowing it to be used via a simulated Kobold API endpoint.

What does it mean? You get llama.cpp with a fancy UI, persistent stories, editing tools, save formats, memory, world info, author's note, characters, scenarios and everything Kobold and Kobold Lite have to offer. In a tiny package under 1 MB in size, excluding model weights.

Preview

Usage

  • Download the latest release here or clone the repo.
  • Windows binaries are provided in the form of llamacpp-for-kobold.exe, which is a pyinstaller wrapper for llamacpp.dll and llamacpp_for_kobold.py. If you feel concerned, you may prefer to rebuild it yourself with the provided makefiles and scripts.
  • Weights are not included, you can use the quantize.exe to generate them from your official weight files (or download them from other places).
  • To run, execute llamacpp-for-kobold.exe or drag and drop your quantized ggml_model.bin file onto the .exe, and then connect with Kobold or Kobold Lite.
  • By default, you can connect to http://localhost:5001
  • You can also run it using the command line llamacpp-for-kobold.exe [ggml_model.bin] [port]. For info, please check llamacpp-for-kobold.exe --help
  • If you are having crashes or issues with OpenBLAS, please try the --noblas flag.

OSX and Linux

  • You will have to compile your binaries from source. A makefile is provided, simply run make
  • After all binaries are built, you can run the python script with the command llamacpp_for_kobold.py [ggml_model.bin] [port]

Considerations

  • Don't want to use pybind11 due to dependencies on MSVCC
  • ZERO or MINIMAL changes as possible to parent repo files - do not move their function declarations elsewhere! We want to be able to update the repo and pull any changes automatically.
  • No dynamic memory allocation! Setup structs with FIXED (known) shapes and sizes for ALL output fields. Python will ALWAYS provide the memory, we just write to it.
  • No external libraries or dependencies. That means no Flask, Pybind and whatever. All You Need Is Python.
  • Since v1.0.6, requires libopenblas, the prebuilt windows binaries are included in this repo. If not found, it will fall back to a mode without BLAS. If you want you can also link your own install of OpenBLAS manually with LLAMA_OPENBLAS=1
  • I plan to keep backwards compatibility with ALL past llama.cpp AND alpaca.cpp models. But you are also encouraged to reconvert/update your models if possible for best results.

License

  • The original GGML library and llama.cpp by ggerganov are licensed under the MIT License
  • However, Kobold Lite is licensed under the AGPL v3.0 License
  • The provided python ctypes bindings in llamacpp.dll are also under the AGPL v3.0 License

Notes

  • Generation delay scales linearly with original prompt length. See this discussion. If OpenBLAS is enabled then prompt ingestion becomes about 2-3x faster. This is automatic on windows, but will require linking on OSX and Linux.
  • I have heard of someone claiming a false AV positive report. The exe is a simple pyinstaller bundle that includes the necessary python scripts and dlls to run. If this still concerns you, you might wish to rebuild everything from source code using the makefile, and you can rebuild the exe yourself with pyinstaller by using make_pyinstaller.bat