transformerlab-app
transformerlab-app copied to clipboard
transformerlab
Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.
If you have a lot of models the import modal overflows off the bottom of the screen and you can't access the "cancel" or "import" buttons.
We've had a number of users get the error about not having validation data when training. Can we somehow check this before starting training and provide the user with a...
It looks like as part of the update to use the mlx_lx, we not longer halt if the training dataset doesn't contain validation data. As a result, no adapter is...
right now if you enter a huggingface model manually, we don't display a progress bar
Bumps the npm_and_yarn group with 1 update: [webpack](https://github.com/webpack/webpack). Updates `webpack` from 5.93.0 to 5.94.0 Release notes Sourced from webpack's releases. v5.94.0 Bug Fixes Added runtime condition for harmony reexport checked...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
To replicate: - disconnect wifi / internet - start app using `npm start`
More details needed but I noticed that most models I train with MLX and some other trained models I download have an issue when running MLX server. The response from...
This mentions a step to remove sandboxing, needed to make Linux app work: https://discord.com/channels/1190722550674755595/1195384493582864515/1290054897202495558
Metadata
Owner
Metadata
Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.