-
It actually works (in Firefox)
-
Supportive multiline in huggingface readme.
-
Remove serve, it's no longer needed.
-
Remove deploy outputs.
-
For hugging face.
-
Better handling of build.
-
Another take for copying.
-
Specifc version?
-
Trying with just index*.* files
-
Again, excluding the weird files.
-
Further build change: shallow checkout, restricted file paths.
-
Different deploy now.
-
Remove stray file, update build.
-
Update workflow to deploy to GitHub Pages
This workflow deploys the project to GitHub Pages after building it. -
Adding WebLLM backend as an option.
-
Fully working version at last.
-
Disabling model discovery for now.
-
Not fully meade.
-
Slash-loading regardless of lookup.
-
Hide menu on escape or click the item.
-
Slash menu style tweaks.
-
Slight tune for the menu.
-
Simpler menu.
-
Slash: attempt to fix.
-
Faster fetching of model list (with caching).
-
Reflect model count.
-
Model load fixes.
-
Worker loading model list tied into the UI.
-
UI integration plan.
-
Followup on worker.
-
Core refactoring of list-chat-models, and a plan for the follow-up.
-
Prepare to refactror worker model list loader.
-
Implemented the worker methods.
-
Detailed steps for worker.
-
Small plan updates.
-
Move with the chosen plan.
-
Trying to improve filtering.
-
Async loading of the slash/models.
-
Cache model list for network failures.
-
Tweaking model list a little.
-
Caching slash-loaded models to use.
-
Handling early output better.
-
Improved model filtering.
-
Better icons for model loading.
-
Slash menu now lists the models.
-
Loading models into slash.
-
Enabling more natural styling and slash menu.
-
REmove dodgy styles.
-
Crepe input.
-
Preparing to slash commands (for list of models and switch model).
