Instructions to use remiai3/RemiAI_Framework with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use remiai3/RemiAI_Framework with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="remiai3/RemiAI_Framework",
	filename="engine/model.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use remiai3/RemiAI_Framework with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf remiai3/RemiAI_Framework
# Run inference directly in the terminal:
llama-cli -hf remiai3/RemiAI_Framework

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf remiai3/RemiAI_Framework
# Run inference directly in the terminal:
llama-cli -hf remiai3/RemiAI_Framework

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf remiai3/RemiAI_Framework
# Run inference directly in the terminal:
./llama-cli -hf remiai3/RemiAI_Framework

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf remiai3/RemiAI_Framework
# Run inference directly in the terminal:
./build/bin/llama-cli -hf remiai3/RemiAI_Framework

Use Docker

docker model run hf.co/remiai3/RemiAI_Framework

LM Studio
Jan

vLLM

How to use remiai3/RemiAI_Framework with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "remiai3/RemiAI_Framework"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "remiai3/RemiAI_Framework",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/remiai3/RemiAI_Framework

Ollama
How to use remiai3/RemiAI_Framework with Ollama:
```
ollama run hf.co/remiai3/RemiAI_Framework
```

Unsloth Studio new

How to use remiai3/RemiAI_Framework with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for remiai3/RemiAI_Framework to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for remiai3/RemiAI_Framework to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for remiai3/RemiAI_Framework to start chatting

Docker Model Runner
How to use remiai3/RemiAI_Framework with Docker Model Runner:
```
docker model run hf.co/remiai3/RemiAI_Framework
```

Lemonade

How to use remiai3/RemiAI_Framework with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull remiai3/RemiAI_Framework

Run and chat with the model

lemonade run user.RemiAI_Framework-{{QUANT_TAG}}

List all available models

lemonade list

RemiAI Open Source Framework

A "No-Setup" Local AI Framework for Students

This project is an open-source, offline AI chat application designed for students and colleges. It allows you to run powerful LLMs (like Llama 3, Mistral, etc.) on your laptop without needing GPU, internet, Python, or complicated installations.

Note - No need any GPU in your laptop to run, it will use the CPU in your laptop for the response generation(inference) and if you want to modify the project code and use another model make sure that your are using the `.gguf` formated weights only, normal weights like `.safetensors` will not supported in this application.

🚀 Quick Start (One-Line Command)

If you have Git and Node.js installed, open your terminal (Command Prompt or PowerShell) and run:

for powershell

git clone https://huggingface.co/remiai3/RemiAI_Framework; cd RemiAI_Framework; git lfs install; git lfs pull; npm install; npm start

for cmd

git clone https://huggingface.co/remiai3/RemiAI_Framework && cd RemiAI-App && git lfs install && git lfs pull && npm install && npm start

⚠️ IMPORTANT: Git LFS Required

This repository uses Git Large File Storage (LFS) for the AI engine binaries. If you download the ZIP or clone without LFS, the app will not work (Error: "RemiAI engine missing").

Pack the entire project into .exe file installer Run the command:

npm run dist

This will create an installer in the release folder that you can share with friends!

if you are facing errors while package or bundle open the power shell as an administrator and run the above command then it will works 100%

💻 Manual Installation

1. Requirements

Node.js: Download Here (Install the LTS version).
Git & Git LFS: Download Git | Download Git LFS
Windows Laptop: (Code includes optimized .exe binaries for Windows).

2. Download & Setup

Download the project zip (or clone the repo).
Extract the folder.
Open Terminal inside the folder path.
Pull Engine Files (Critical Step):
```
git lfs install
git lfs pull
```
Run the installer for libraries:
```
npm install
```

3. Run the App

Simply type:

npm start

The application will launch, the AI engine will start in the background, and you can begin chatting immediately!

📦 Features

Zero Python Dependency: We use compiled binaries (.dll and .exe included) so you don't need to install Python, PyTorch, or set up virtual environments.
Plug & Play Models: Supports .gguf format.
- Want a different model? Download any .gguf file, rename it to model.gguf, and place it in the project root.
Auto-Optimization: Automatically detects your CPU features (AVX vs AVX2) to give you the best speed possible.
Privacy First: Runs 100% offline. No data leaves your device.

❓ Troubleshooting

Error: "RemiAI Engine Missing" This means you downloaded the "pointer" files (130 bytes) instead of the real engine. Fix:

Open terminal in project folder.
Run git lfs install
Run git lfs pull
Restart the app.

🛠️ Credits & License

Created By: RemiAI Team
License: MIT License.
- You are free to rename, modify, and distribute this application as your own project!

Note on Models: The application will only uses the `.gguf` formated weights only to make it as the CPU friendly run the application without any GPU

Downloads last month: 24

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for remiai3/RemiAI_Framework

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Quantized

(177)

this model