Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,121 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# OnLLM π§
|
| 6 |
+
OnLLM is the platform to run `Large Language Model` (LLM) or SLM models using `OnnxRuntime` directly on low-end devices like low power computers, mobile phones etc. It is cross-platform using Kivy & open-source.
|
| 7 |
+
|
| 8 |
+
> The name is derived from: `On` from Onnx + `LLM`. Our approach is always local & offline first (you will need internet to download the model files for the first time). Arificial Intelligence (AI) to be accesible to everyone.
|
| 9 |
+
|
| 10 |
+
### Features
|
| 11 |
+
1. An inbuild chatbot to chat with the AI model(s).
|
| 12 |
+
2. No trackers, no Ads, No data collection, completely Private.
|
| 13 |
+
|
| 14 |
+
[](https://github.com/daslearning-org/OnLLM/releases)
|
| 15 |
+
[](https://www.youtube.com/watch?v=D-KwL59GgKA)
|
| 16 |
+
|
| 17 |
+
## π½οΈ Demo
|
| 18 |
+
You can click on the below Image or this [Youtube Link](https://www.youtube.com/watch?v=D-KwL59GgKA) to see the demo. Please let me know in the comments, how do you feel about this App. <br>
|
| 19 |
+
[](https://www.youtube.com/watch?v=D-KwL59GgKA)
|
| 20 |
+
|
| 21 |
+
## π§ Our Scematic Architecture
|
| 22 |
+
To be added...
|
| 23 |
+
|
| 24 |
+
## π§βπ» Quickstart Guide
|
| 25 |
+
|
| 26 |
+
### π± Download & Run the Android App
|
| 27 |
+
You can check the [Releases](https://github.com/daslearning-org/OnLLM/tags) and downlaod the latest version of the android app (APK file) on your phone.
|
| 28 |
+
|
| 29 |
+
### π» Download & Run the Windows or Linux App
|
| 30 |
+
You can check the [Releases](https://github.com/daslearning-org/OnLLM/releases) and downlaod the latest version of the application on your computer. If you are on `Windows`, download the `OnLLM_X.X.X.exe` file & double click to run it. If you are on `Linux`, download `OnLLM_Linux_XXX` file and run it.
|
| 31 |
+
|
| 32 |
+
#### Notes:
|
| 33 |
+
- Some Antivirus softwares might give you detection alert for the exe (happens for PyInstaller apps), you need to add an exception in that case.
|
| 34 |
+
- On Linux you may need to change file permission to execute it.
|
| 35 |
+
```bash
|
| 36 |
+
chmod +x OnLLM_Linux_XXX
|
| 37 |
+
./OnLLM_Linux_XXX
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
### π Run with Python
|
| 41 |
+
|
| 42 |
+
1. Clone the repo
|
| 43 |
+
```bash
|
| 44 |
+
git clone https://github.com/daslearning-org/OnLLM.git
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
2. Run the application
|
| 48 |
+
```bash
|
| 49 |
+
cd OnLLM/app/
|
| 50 |
+
pip install -r requirements.txt # virtual environment is recommended
|
| 51 |
+
python main.py
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
## π¦Ύ Build your own App
|
| 55 |
+
The Kivy project has a great tool named [Buildozer](https://buildozer.readthedocs.io/en/latest/) which can make mobile apps for `Android` & `iOS`
|
| 56 |
+
|
| 57 |
+
### π± Build Android App
|
| 58 |
+
A Linux environment is recommended for the app development. If you are on Windows, you may use `WSL` or any `Virtual Machine`. As of now the `buildozer` tool works on Python version `3.11` at maximum. I am going to use Python `3.11`
|
| 59 |
+
|
| 60 |
+
#### Install Rust & Add that in path
|
| 61 |
+
```bash
|
| 62 |
+
curl https://sh.rustup.rs -sSf | sh # then follow the prompt
|
| 63 |
+
export PATH="$HOME/.cargo/bin:$PATH"
|
| 64 |
+
# optional
|
| 65 |
+
rustup default stable
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
#### Install other dependencies & build APK
|
| 69 |
+
```bash
|
| 70 |
+
# add the python repository
|
| 71 |
+
sudo add-apt-repository ppa:deadsnakes/ppa
|
| 72 |
+
sudo apt update
|
| 73 |
+
|
| 74 |
+
# install all dependencies.
|
| 75 |
+
sudo apt install -y ant autoconf automake ccache cmake g++ gcc libbz2-dev libffi-dev libltdl-dev libtool libssl-dev lbzip2 make ninja-build openjdk-17-jdk patch patchelf pkg-config protobuf-compiler python3.11 python3.11-venv python3.11-dev
|
| 76 |
+
|
| 77 |
+
# optionally we can default to python 3.11
|
| 78 |
+
sudo ln -sf /usr/bin/python3.11 /usr/bin/python3
|
| 79 |
+
sudo ln -sf /usr/bin/python3.11 /usr/bin/python
|
| 80 |
+
sudo ln -sf /usr/bin/python3.11-config /usr/bin/python3-config
|
| 81 |
+
|
| 82 |
+
# optionally you may check the java installation with below commands
|
| 83 |
+
java -version
|
| 84 |
+
javac -version
|
| 85 |
+
|
| 86 |
+
# install python modules
|
| 87 |
+
git clone https://github.com/daslearning-org/OnLLM.git
|
| 88 |
+
cd OnLLM/app/
|
| 89 |
+
python3.11 -m venv .env # create python virtual environment
|
| 90 |
+
source .env/bin/activate
|
| 91 |
+
pip install -r req_android.txt
|
| 92 |
+
|
| 93 |
+
# build the android apk
|
| 94 |
+
buildozer android debug # this may take a good amount of time for the first time & will generate the apk in the bin directory
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
### π³ Build Computer Application (Windows / Linux / MacOS)
|
| 98 |
+
A `Python` virtual environment is recommended and will use `PyInstaller` to package it.
|
| 99 |
+
|
| 100 |
+
```bash
|
| 101 |
+
# install pyinstaller
|
| 102 |
+
git clone https://github.com/daslearning-org/OnLLM.git
|
| 103 |
+
cd OnLLM/app/
|
| 104 |
+
python3.11 -m venv .env # create python virtual environment
|
| 105 |
+
source .env/bin/activate
|
| 106 |
+
pip install -r requirements.txt
|
| 107 |
+
pip install pyinstaller
|
| 108 |
+
|
| 109 |
+
# then update the spec file as needed
|
| 110 |
+
# then build your app which will be native to the OS i.e. Linux or Windows or MAC
|
| 111 |
+
pyinstaller desktopApp.spec
|
| 112 |
+
```
|
| 113 |
+
|
| 114 |
+
## π LLM Models used in this project
|
| 115 |
+
The models are being taken from different sources & below are the models available as on today. Size is the compressed size (approax).
|
| 116 |
+
|
| 117 |
+
| Model | Size | Android | Desktop |
|
| 118 |
+
| :---- | :--- | :-----: | :-----: |
|
| 119 |
+
| [SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) | 95MB | β
οΈ | β
οΈ |
|
| 120 |
+
| [SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) | 241MB | β
οΈ | β
οΈ |
|
| 121 |
+
| [Gemma3-1B](https://huggingface.co/onnx-community/gemma-3-1b-it-ONNX) | 1GB | β | β
οΈ |
|