Forwarded from Libreware
ChatterUI - A simple app for LLMs
https://github.com/Vali-98/ChatterUI
https://t.me/chatterui
ChatterUI is a native mobile frontend for LLMs.
Run LLMs on device or connect to various commercial or open source APIs. ChatterUI aims to provide a mobile-friendly interface with fine-grained control over chat structuring.
Features:
Run LLMs on-device in Local Mode
Connect to various APIs in Remote Mode
Chat with characters. (Supports the Character Card v2 specification.)
Create and manage multiple chats per character.
Customize Sampler fields and Instruct formatting
Integrates with your device’s text-to-speech (TTS) engine
Usage
Download and install latest APK from the releases page.
iOS is Currently unavailable due to lacking iOS hardware for development
Local Mode
ChatterUI uses a llama.cpp under the hood to run gguf files on device. A custom adapter is used to integrate with react-native: cui-llama.rn
To use on-device inferencing, first enable Local Mode, then go to Models > Import Model / Use External Model and choose a gguf model that can fit on your device's memory. The importing functions are as follows:
Import Model: Copies the model file into ChatterUI, potentially speeding up startup time.
Use External Model: Uses a model from your device storage directly, removing the need to copy large files into ChatterUI but with a slight delay in load times.
After that, you can load the model and begin chatting!
Note: For devices with Snapdragon 8 Gen 1 and above or Exynos 2200+, it is recommended to use the Q4_0 quantization for optimized performance.
Remote Mode
Remote Mode allows you to connect to a few common APIs from both commercial and open source projects.
Open Source Backends:
koboldcpp
text-generation-webui
Ollama
Dedicated API:
OpenAI
Claude (with ability to use a proxy)
Cohere
Open Router
Mancer
AI Horde
Generic backends:
Generic Text Completions
Generic Chat Completions
These should be compliant with any Text Completion/Chat Completion backends such as Groq or Infermatic.
Custom APIs:
Is your API provider missing? ChatterUI allows you to define APIs using its template system.
Read more about it here!
#ai #Android
https://github.com/Vali-98/ChatterUI
https://t.me/chatterui
ChatterUI is a native mobile frontend for LLMs.
Run LLMs on device or connect to various commercial or open source APIs. ChatterUI aims to provide a mobile-friendly interface with fine-grained control over chat structuring.
Features:
Run LLMs on-device in Local Mode
Connect to various APIs in Remote Mode
Chat with characters. (Supports the Character Card v2 specification.)
Create and manage multiple chats per character.
Customize Sampler fields and Instruct formatting
Integrates with your device’s text-to-speech (TTS) engine
Usage
Download and install latest APK from the releases page.
iOS is Currently unavailable due to lacking iOS hardware for development
Local Mode
ChatterUI uses a llama.cpp under the hood to run gguf files on device. A custom adapter is used to integrate with react-native: cui-llama.rn
To use on-device inferencing, first enable Local Mode, then go to Models > Import Model / Use External Model and choose a gguf model that can fit on your device's memory. The importing functions are as follows:
Import Model: Copies the model file into ChatterUI, potentially speeding up startup time.
Use External Model: Uses a model from your device storage directly, removing the need to copy large files into ChatterUI but with a slight delay in load times.
After that, you can load the model and begin chatting!
Note: For devices with Snapdragon 8 Gen 1 and above or Exynos 2200+, it is recommended to use the Q4_0 quantization for optimized performance.
Remote Mode
Remote Mode allows you to connect to a few common APIs from both commercial and open source projects.
Open Source Backends:
koboldcpp
text-generation-webui
Ollama
Dedicated API:
OpenAI
Claude (with ability to use a proxy)
Cohere
Open Router
Mancer
AI Horde
Generic backends:
Generic Text Completions
Generic Chat Completions
These should be compliant with any Text Completion/Chat Completion backends such as Groq or Infermatic.
Custom APIs:
Is your API provider missing? ChatterUI allows you to define APIs using its template system.
Read more about it here!
#ai #Android
GitHub
GitHub - Vali-98/ChatterUI: Simple frontend for LLMs built in react-native.
Simple frontend for LLMs built in react-native. Contribute to Vali-98/ChatterUI development by creating an account on GitHub.
Forwarded from Libreware
Maid - Mobile Artificial Intelligence Distribution
Maid is a cross-platform free and an open-source application for interfacing with llama.cpp models locally, and remotely with Ollama, Mistral, Google Gemini and OpenAI models remotely.
-Choose from A wide range of models that runs LOCALLY and access remote models via api key!
-Text based output
-Image Generation (Selected Models only)
-No video or short clips generation yet
-Voice generation on selected models (Not tested)
-Setting model parameters
-Setting system prompt (Making the model behave/generate output in a certain way).
-And more.
Get it on
Github - https://github.com/Mobile-Artificial-Intelligence/maid/releases/latest
Fdroid - https://f-droid.org/packages/com.danemadsen.maid/
Spystore - https://play.google.com/store/apps/details?id=com.danemadsen.maid
*Don't clear CACHE OF THE APP AND EXCLUDE IT FROM SYSTEM'S AUTO CACHE CLEANING as app stores everything in device cache*
Follow @nogoolag and @libreware for more
#ai
Maid is a cross-platform free and an open-source application for interfacing with llama.cpp models locally, and remotely with Ollama, Mistral, Google Gemini and OpenAI models remotely.
-Choose from A wide range of models that runs LOCALLY and access remote models via api key!
-Text based output
-Image Generation (Selected Models only)
-No video or short clips generation yet
-Voice generation on selected models (Not tested)
-Setting model parameters
-Setting system prompt (Making the model behave/generate output in a certain way).
-And more.
Get it on
Github - https://github.com/Mobile-Artificial-Intelligence/maid/releases/latest
Fdroid - https://f-droid.org/packages/com.danemadsen.maid/
Spystore - https://play.google.com/store/apps/details?id=com.danemadsen.maid
*Don't clear CACHE OF THE APP AND EXCLUDE IT FROM SYSTEM'S AUTO CACHE CLEANING as app stores everything in device cache*
Follow @nogoolag and @libreware for more
#ai
Forwarded from Libreware
Libreware
Photo
Maid is heating up my phone and draining battery. I don't recommend it for lower end phones. If snapdragon 8 gen 2 is behaving like this, lower end phones will fail to run this app
Anyway, it runs without internet!
Anyway, it runs without internet!
Forwarded from GSMArena (IFTTT)
Oppo exec officially reveals the Find X9 and Find X9 Pro's battery capacity, more details
https://ift.tt/mBRQ1fG
https://ift.tt/mBRQ1fG
GSMArena.com
Oppo exec officially reveals the Find X9 and Find X9 Pro's battery capacity, more details
The Find series product manager is a true treasure trove of information. Oppo is expected to launch the Find X9 and Find X9 Pro in October, and ahead of...
Forwarded from GSMArena (IFTTT)
Lava Bold N1 5G arrives with a 90Hz display, three years of software updates, and a sub-$100 price tag
https://ift.tt/r7iKZ5T
https://ift.tt/r7iKZ5T
GSMArena.com
Lava Bold N1 5G arrives with a 90Hz display, an IP54 rating, and a sub-$100 price tag
It comes with bloatware-free Android. Lava launched the Lava Bold N1 4G in June, and today, the brand unveiled the 5G model.
The Lava Bold N1 5G has the...
The Lava Bold N1 5G has the...
Forwarded from #TBOT: Take Back Our Tech
Media is too big
VIEW IN TELEGRAM
⚡️Enoch AI for Real Information: Free Access
Finally, an uncensored AI trained on knowledge that’s often buried or ignored by mainstream engines. Enoch AI, built by Brighteon, brings you real information on natural health, nutrition, permaculture, self-reliance, history, and more.
It’s trained on GreenMedInfo, Children’s Health Defense, Mercola, Natural News, Decentralized TV, and even hundreds of survival and off-grid living books from around the world.
I tested it for myself. Enoch AI is fast, practical, and actually useful.
Try it for free:
👉 brighteon.ai (email answers)
👉enochvip.consumerwellness.org (real-time chat)
And soon, a self-hosted version will be available on Above Phone and Above Book—no internet connection required!
This solution is from #TBOT Show Episode 12. Watch the full episode.
📲Grab privacy gear.
—
🫶 @takebackourtech
📩 WEBSITE & NEWSLETTER | 🎥 VIDEOS| XMPP | SUBSTACK
Finally, an uncensored AI trained on knowledge that’s often buried or ignored by mainstream engines. Enoch AI, built by Brighteon, brings you real information on natural health, nutrition, permaculture, self-reliance, history, and more.
It’s trained on GreenMedInfo, Children’s Health Defense, Mercola, Natural News, Decentralized TV, and even hundreds of survival and off-grid living books from around the world.
I tested it for myself. Enoch AI is fast, practical, and actually useful.
Try it for free:
👉 brighteon.ai (email answers)
👉enochvip.consumerwellness.org (real-time chat)
And soon, a self-hosted version will be available on Above Phone and Above Book—no internet connection required!
This solution is from #TBOT Show Episode 12. Watch the full episode.
📲Grab privacy gear.
—
🫶 @takebackourtech
📩 WEBSITE & NEWSLETTER | 🎥 VIDEOS| XMPP | SUBSTACK
Forwarded from Bones' Tech Garage
When searching for a Music Player for Linux, I was coming from Windows, and using Media Jukebox (now retired). The closest thing that I could find was Tauon, which works great, with a couple of quirks, and displays my Media, complete with Album Art.
The quirks are minor, but easily solvable. Follow me. This is easy! First, download Tauon here..
https://github.com/Taiko2k/Tauon
Or from your Distros Repo. Run the Install, and configure it. Drag and Drop your Music Folder into the Navigation Pane. Its that easy. Tauon will import and remember everything .. except .. if you keep your Music on a Removable Drive, like I do. The Fix is in the next Post.
The quirks are minor, but easily solvable. Follow me. This is easy! First, download Tauon here..
https://github.com/Taiko2k/Tauon
Or from your Distros Repo. Run the Install, and configure it. Drag and Drop your Music Folder into the Navigation Pane. Its that easy. Tauon will import and remember everything .. except .. if you keep your Music on a Removable Drive, like I do. The Fix is in the next Post.
GitHub
GitHub - Taiko2k/Tauon: The music player of today! :city_sunrise:
The music player of today! :city_sunrise:. Contribute to Taiko2k/Tauon development by creating an account on GitHub.
Forwarded from Bones' Tech Garage
The Fix for the above quirk involves Flatpack Permissions. Honestly, I don't like Flatpacks, but sometimes they're a necessary evil. The quirk I was experiencing was the Music I have resides on a 1.5 TB SD Card, that I use as a D Drive on my Surface Pro 4. Tauon kept dumping the Imported Path to the Music after every Reboot. With the most recent Update, I again launched Tauon after the Reboot, but again had to clear the ghosted Database, and try to import. This time, it popped a message about Flatpack Permissions, and led me to a Webpage with a Flatpack Permissions Tool, where I could fix this problem, add the persistence I needed, granularly, and see what else the Flatpack Permissions were able to do, or not do in my System. BONUS, this small GUI also picked up the other Flat Packs I have, and allowed me to inspect them, and change permissions on those Programs as well! 😉
The additional Program for Permissions is called Flatseal, and was in the Fedora Repo. It will most likely be in your Distros Repo too. Small, effective. Read about it with respect to Tauon here.
https://github.com/Taiko2k/Tauon/wiki/Flatpak-Extra-Steps
The additional Program for Permissions is called Flatseal, and was in the Fedora Repo. It will most likely be in your Distros Repo too. Small, effective. Read about it with respect to Tauon here.
https://github.com/Taiko2k/Tauon/wiki/Flatpak-Extra-Steps
GitHub
Flatpak Extra Steps
The music player of today! :city_sunrise:. Contribute to Taiko2k/Tauon development by creating an account on GitHub.
Forwarded from Bones' Tech Garage
For a little more information on Flatpack Permissions and how things work, this Page by the same Author gets under the hood a little. Enjoy the new Knowledge!
https://github.com/Taiko2k/Tauon/wiki/Sandboxing-Quirks
https://github.com/Taiko2k/Tauon/wiki/Sandboxing-Quirks
GitHub
Sandboxing Quirks
The music player of today! :city_sunrise:. Contribute to Taiko2k/Tauon development by creating an account on GitHub.
No deleted account found from
84 scanned users from this group 🚫👻