llamafile VS plantuml

Do you want that integrated in the browser? Because Mozilla already distributes offline LLMs: https://github.com/Mozilla-Ocho/llamafile

See https://github.com/Mozilla-Ocho/llamafile, a standalone packaging of llama.cpp that runs an LLM locally. It will use the GPU, but it also falls back on the CPU. CPU performance of small, quantized models is still pretty decent, and the page has estimated memory requirements for different models.

I think the llamafile[0] system works the best. Binary works on the command line or launches a mini webserver. Llamafile offers builds of Mixtral-8x7B-Instruct, so presumably they may package this one up as well (potentially a quantized format).

You would have to confirm with someone deeper in the ecosystem, but I think you should be able to run this new model as is against a llamafile?

[0] https://github.com/Mozilla-Ocho/llamafile

Thermostats: https://www.sinopetech.com/en/products/thermostat/

I haven't tried running a local text-to-speech engine backed by an LLM to control Home Assistant. Maybe someone is working on this already?

TTS: https://github.com/SYSTRAN/faster-whisper

LLM: https://github.com/Mozilla-Ocho/llamafile/releases

LLM: https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-D...

It would take some tweaking to get the voice commands working correctly.

While I did not succeed in making the matmul code from https://github.com/Mozilla-Ocho/llamafile/blob/main/llamafil... work in isolation, I compared eigen, openblas, and mkl: https://gist.github.com/Dobiasd/e664c681c4a7933ef5d2df7caa87...

In this (very primitive!) benchmark, MKL was a bit better than eigen (~10%) on my machine (i5-6600).

Since the article https://justine.lol/matmul/ compared the new kernels with MLK, we can (by transitivity) compare the new kernels with Eigen this way, at least very roughly for this one use-case.

Yes, they're just ZIP files that also happen to be actually portable executables.

https://github.com/Mozilla-Ocho/llamafile?tab=readme-ov-file...

PlantUML, like Mermaid, is an open source tool that allows users to create diagrams from plain text descriptions. PlantUML is the original ‘diagrams as code’ platform. It has a deep feature set, can be integrated into just about any environment, and can be extended to fit just about any use case. For example, the most useful thing to me about PlantUML is its support for visualizing .JSON files.

New version 3.0 of my PlantUML App for iPad is out with exciting update! 🤩 The new multi-modality feature now lets you transform hand-drawn diagrams into PlantUML scripts with just a pencil ✍🏻 or your fingers 👆. Take a look 👀 to this short on YouTube and download it from App Store to support me 👍🏻.

Someone at work showed me https://plantuml.com/ recently. If you want your diagrams as code . Version controlled etc.. I highly recommend it.

Maybe try PlantUML.

Open-source tool that uses simple textual descriptions to draw beautiful UML diagrams.

Seems like a considerable upgrade from PlanUML (https://plantuml.com/ - which is amazing, but sometimes you just can't seem to be able to align the stuff the way you want too).

plantuml is amongst the best there is. kroki.io has a sandbox for it mermaid.js can do it in notion, it works as well as any other mermaid. dbvisualizer is fantastic if you have an existing schema in a db instance. you may need the trial license to render the diagrams

PlantUML ima podsku za mnogo vise dijagrama - https://plantuml.com/ (bar za sada).

I mean, I know about PlantUML where you can write code that will generate cool diagrams and it's feels like one of solutions\implementations but not the right one. What actual way people in huge companies create UML diagrams for their projects? I can't find any software or language syntax, even guides on Youtube about UML is just hours of talking about all sorts of UML diagrams without ever mentioning any software or syntax or actual way to create them.