koboldai: init #3
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This removes the need to have multiple output variations like invokeai-wsl-amd and instead just uses a simple bash wrapper to discover whether the program is being ran in the WSL
MatthewCroughan
force-pushed
the
mc/kobold-ai
branch
from
28d84cc
to
1a436db
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
kobold-ai is a web interface for interacting with "transformers" models https://huggingface.co/docs/transformers/index
The wrapper script will automatically put its state in
~/.koboldai/statewhen ran, and it will also take care of settingLD_LIBRARY_PATHif the program is being ran in the Windows Subsystem for Linux so that it can make use of the GPU in that contextI've also updated InvokeAI in this PR to do the same, which removes the
invokeai-wsl-nvidiaandinvokeai-wsl-amdoutputs as they are no longer required, as running the program in WSL now just automatically work.A GPU is not required, and either the NVIDIA or AMD output will operate in CPU mode when a GPU is not detected
Below is an example of how to launch it, as well as a screenshot of the web interface working with a simple GPT2 model, it took 3 seconds to compute on a Ryzen 5950x. The generated text is highlighted, whereas the input text is not highlighted
This PR also adds an AUTHORS file which specifies the current maintainers, I'm copying the format from https://github.com/openzfs/zfs/blob/master/AUTHORS