I'm having a lot of fun chatting with characters using Faraday and koboldcpp. Faraday has a great UI that lets you adjust character profiles, generate alternative model responses, undo, or edit dialogue, and experiment with how models react to your input. There's also SillyTavern that I have yet to try out.
I hate this kind of clickbait marketing suggesting the project is delivering 1/100 of the size or 100x-35000x the speed of other solutions because it uses a different language for a wrapper around core library and completely neglecting tooling and community expertise built around other solutions.
First of all the project is based on llama.cpp[1], which does the heavy work of loading and running multi-GB model files on GPU/CPU and the inference speed is not limited by the wrapper choice (there are other wrappers in Go, Python, Node, Rust, etc. or one can use llama.cpp directly). The size of the binary is also not that important when common quantized model files are often in the range of 5GB-40GB and require a beefy GPU or a MB with 16-64GB of RAM.
I’m using Jupyter Book (https://jupyterbook.org/) to build all kinds of daily reports and it works really well.
Individual notebooks can also be converted to HTML or pdf with nbconvert using command line or “download as” menu item.
Mine came with a manual in German and some hardly readable photocopy of a translation written on a typewriter. That was a steep learning curve for a kid. Fortunately there were a lot of young and older folks who shared knowledge, engaged into demo scene or just played games. Later on I got a couple books and subscribed to the C&A magazine which helped me a lot with diving into graphics programming, extension ports, SID, etc.
The best part about C64 was it immediately booted into a Basic prompt that invited you to experiment with the hardware, like typing these magic POKE commands to set screen and text colors.
Just guessing, but there may be other devices providing DNS service on your network. For example I have found that AppleTV is listening for DNS queries on a couple ports and MacOS will happily fallback to that.
Wavelets are fun. I first heard about them in the early 2000s when I read about JPEG 2000 image compression format [1]. Back then the primary tool to play with signal transformation was the Matlab Wavelet Toolbox. As I got more interested in the topic I started work on PyWavelets [2] Python package for my master's thesis about medical signals processing and ML classification.
I'm not actively involved in the package development anymore but it is still maintained [3] and there is a great chance that you have it already in your Python environment as a dependency of scikit-image/scikit-learn. Just give it a try, it's very simple:
>>> import pywt
>>> cA, cD = pywt.dwt([1, 2, 3, 4], 'db1')
There are many reasons for using other databases like PostgreSQL or MySQL in production - feature set, (managed) hosting, backup and replication, etc.
SQLite is primarily embedded/local database and cannot be easily separated and shared over network [1] between multiple disposable backend/worker instances.
- https://faraday.dev/
- https://github.com/LostRuins/koboldcpp
- https://github.com/SillyTavern/SillyTavern