llamafile
photopea
llamafile | photopea | |
---|---|---|
38 | 147 | |
16,040 | 7,046 | |
33.1% | - | |
9.6 | 4.2 | |
3 days ago | 30 days ago | |
C++ | ||
GNU General Public License v3.0 or later | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llamafile
- FLaNK-AIM Weekly 06 May 2024
- llamafile v0.8
-
Mistral AI Launches New 8x22B Moe Model
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
-
Apple Explores Home Robotics as Potential 'Next Big Thing'
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.
-
LLaMA Now Goes Faster on CPUs
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.
-
Llamafile 0.7 Brings AVX-512 Support: 10x Faster Prompt Eval Times for AMD Zen 4
Yes, they're just ZIP files that also happen to be actually portable executables.
https://github.com/Mozilla-Ocho/llamafile?tab=readme-ov-file...
-
Show HN: I made an app to use local AI as daily driver
have you seen llamafile[0]?
[0] https://github.com/Mozilla-Ocho/llamafile
- FLaNK Stack 26 February 2024
-
Gemma.cpp: lightweight, standalone C++ inference engine for Gemma models
llama.cpp has integrated gemma support. So you can use llamafile for this. It is a standalone executable that is portable across most popular OSes.
https://github.com/Mozilla-Ocho/llamafile/releases
So, download the executable from the releases page under assets. You want either just main or just server. Don't get the huge ones with the model inlined in the file. The executable is about 30MB in size,
https://github.com/Mozilla-Ocho/llamafile/releases/download/...
-
Ollama releases OpenAI API compatibility
The improvements in ease of use for locally hosting LLMs over the last few months have been amazing. I was ranting about how easy https://github.com/Mozilla-Ocho/llamafile is just a few hours ago [1]. Now I'm torn as to which one to use :)
1: Quite literally hours ago: https://euri.ca/blog/2024-llm-self-hosting-is-easy-now/
photopea
- FLaNK Stack 26 February 2024
-
The Photopea Logo on Software Homepage (Usage?)
As long as it refers to www.Photopea.com , and you are not using our name or logo to represent your own product, I think it is fine :)
-
A Simple Performance Benchmark
Hi guys, I am the creator of www.Photopea.com - a photo editor in a browser.
-
Is there a way for the uploaded fonts to stay saved?
When you load your own TTF or OTF font to www.Photopea.com , Photopea should offer you to keep this font in the Local Storage. Are you asked about it?
-
PNGs edited with Photopea not loading on other websites.
Maybe look here: https://github.com/photopea/photopea/issues/6196
-
For New Users
No, you just need to open www.Photopea.com , do what you need and press File - Save, to save a file (into your computer).
- 'Background Replace' not working for anyone else??
-
Suddenly can't use Photopea due to a message reading "Please, let us show you ads ("Change Consent" on the right), or get a Premium account ("Account" at the top) and reload Photopea."
Could you show us a screenshot of how www.Photopea.com looks for you? Also, did you try to change the consent and allow ads?
-
Underline text results in a segmented line
No problem - that is something that should work like in Photoshop. Try to add this as a bug on the Photopeas' GitHub. Just sign in/up and add new issue here https://github.com/photopea/photopea/issues
-
Cannot access on public networks due to link to Pixbay
Hey there folks. Just wanted to share this here in case others had the same issue. I'm attempting to open Photopea on a public network but have been unsuccessful to connect to the site (yes I've done all the troubleshooting). I found this thread on github (https://github.com/photopea/photopea/issues/2951) which basically helped me solve my issue: Access is denied on public networks that block pornography and since they're linked to Pixbay (who offers adult content), they're blocked by proxy.
What are some alternatives?
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
Photopea-Desktop-App - Offline version of Photopea bundled into a portable electron desktop app.
ollama-webui - ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]
LeetCode - This is my LeetCode solutions for all 2000+ problems, mainly written in C++ or Python.
langchain - 🦜🔗 Build context-aware reasoning applications
photopea - Photopea for offline use [UnavailableForLegalReasons - Repository access blocked]
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
oxipng - Multithreaded PNG optimizer written in Rust
llama.cpp - LLM inference in C/C++
Glimpse - Fork of the GNU Image Manipulation Program 2.10.18
safetensors - Simple, safe way to store and distribute tensors
photopea - Unofficial Photopea for offline use [UnavailableForLegalReasons - Repository access blocked]