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

Libraries

How to use jehanweerasuriya/UniFriendAI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jehanweerasuriya/UniFriendAI",
	filename="mistral-7b-instruct-v0.3.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jehanweerasuriya/UniFriendAI with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jehanweerasuriya/UniFriendAI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jehanweerasuriya/UniFriendAI:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jehanweerasuriya/UniFriendAI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jehanweerasuriya/UniFriendAI:Q4_K_M

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 jehanweerasuriya/UniFriendAI:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jehanweerasuriya/UniFriendAI:Q4_K_M

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 jehanweerasuriya/UniFriendAI:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jehanweerasuriya/UniFriendAI:Q4_K_M

Use Docker

docker model run hf.co/jehanweerasuriya/UniFriendAI:Q4_K_M

LM Studio
Jan

vLLM

How to use jehanweerasuriya/UniFriendAI with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jehanweerasuriya/UniFriendAI:Q4_K_M

Ollama
How to use jehanweerasuriya/UniFriendAI with Ollama:
```
ollama run hf.co/jehanweerasuriya/UniFriendAI:Q4_K_M
```

Unsloth Studio

How to use jehanweerasuriya/UniFriendAI 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 jehanweerasuriya/UniFriendAI 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 jehanweerasuriya/UniFriendAI to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use jehanweerasuriya/UniFriendAI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jehanweerasuriya/UniFriendAI:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jehanweerasuriya/UniFriendAI:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jehanweerasuriya/UniFriendAI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jehanweerasuriya/UniFriendAI:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jehanweerasuriya/UniFriendAI:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use jehanweerasuriya/UniFriendAI with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jehanweerasuriya/UniFriendAI:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jehanweerasuriya/UniFriendAI:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use jehanweerasuriya/UniFriendAI with Docker Model Runner:
```
docker model run hf.co/jehanweerasuriya/UniFriendAI:Q4_K_M
```

Lemonade

How to use jehanweerasuriya/UniFriendAI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jehanweerasuriya/UniFriendAI:Q4_K_M

Run and chat with the model

lemonade run user.UniFriendAI-Q4_K_M

List all available models

lemonade list

🎓 UniFriendAI

🚀 AI Learning Assistant for Undergraduate Information Technology Students

Built on Mistral-7B-Instruct and fine-tuned for BSc IT, BTech IT, and related undergraduate computing programmes.

⭐ Designed for Semester 1 & Semester 2 learning.

🌟 Overview

UniFriendAI is a fine-tuned educational Large Language Model (LLM) developed to support undergraduate Information Technology students.

Unlike general-purpose chatbots, UniFriendAI focuses on foundational university-level computing subjects, providing beginner-friendly explanations, programming assistance, study notes, revision material, quizzes, and academic guidance.

🎯 Target Users

👨‍🎓 BSc Information Technology Students

👩‍🎓 BTech Information Technology Students

💻 Computer Science Students

🏫 Universities

🎓 Higher Education Institutes

👨‍🏫 Lecturers

📚 Self Learners

📚 Academic Coverage

✅ Programming Fundamentals – Variables

✅ Python Loops

✅ Functions

✅ Arrays

✅ Object-Oriented Programming Basics

✅ Computer Architecture

✅ Operating System

✅ OSI Model

✅ IP Addressing

✅ SQL

✅ Normalization (1NF, 2NF, 3NF)

✅ ER Diagrams

✅ Software Development Life Cycle (SDLC)

✨ Features

✅ Beginner-Friendly Explanations

✅ Programming Assistance

✅ Assignment Guidance

✅ Quiz Generation

✅ Exam Preparation

✅ Study Notes

✅ Code Explanation

✅ Bug Detection

✅ Algorithm Explanation

✅ Academic Question Answering

🧠 Model Information

Property	Value
Base Model	Mistral-7B-Instruct-v0.3
Quantization	Q4_K_M
Format	GGUF
Parameters	7 Billion
Language	English
License	MIT
Architecture	Transformer
Intended Use	Educational AI Assistant

💻 Individual / Student Requirements

⚙️ Minimum (CPU Only)

Perfect for budget laptops.

Component	Requirement
RAM	8 GB DDR4
CPU	Intel Core i3 / AMD Ryzen 3
GPU	Integrated Graphics
Storage	10 GB Free
Runtime	CPU Only

Performance

🐢 2–5 words/sec

Close Chrome, Discord and other heavy applications for best performance.

🚀 Recommended

Best experience for most students.

Component	Requirement
RAM	16 GB DDR4/DDR5
CPU	Intel Core i5 / Ryzen 5
GPU	GTX 1650 / RTX 2050 / RTX 3050 / RX6500XT
VRAM	4–6 GB
Storage	SSD

Performance

⚡ 12–20 words/sec

Ollama automatically shares memory between RAM and GPU for smooth inference.

🔥 High Performance

For enthusiasts and power users.

Component	Requirement
RAM	16–32 GB DDR5
CPU	Intel Core i7 / Ryzen 7
GPU	RTX 3060 / RTX 4060 or better
Apple	Apple Silicon M1/M2/M3/M4 (16 GB+)
Storage	NVMe SSD

Performance

🚀 35–50+ words/sec

Entire model fits into GPU memory for ultra-fast inference.

🏫 Institutional Deployment

UniFriendAI is suitable for deployment in universities, colleges, schools, and training institutes.

🖥 Recommended Server

Component	Recommendation
CPU	AMD EPYC / Intel Xeon
RAM	64–128 GB ECC
GPU	RTX 4090 / RTX A6000 / NVIDIA L40S / A100
Storage	500 GB+ NVMe SSD
OS	Ubuntu Server 24.04 LTS

🔐 Production Features

✅ API Keys

✅ JWT Authentication

✅ OAuth Support

✅ HTTPS

✅ SSL/TLS

✅ Rate Limiting

✅ Request Logging

✅ Analytics Dashboard

✅ User Management

✅ Role-Based Access Control (RBAC)

✅ Multi-Tenant Support

✅ Response Caching

✅ Conversation History

✅ Monitoring

✅ Backup & Recovery

✅ Docker Deployment

✅ Kubernetes Ready

✅ LMS Integration

✅ Moodle Integration

✅ Blackboard Integration

✅ Canvas LMS Integration

✅ PDF Knowledge Base

✅ Retrieval-Augmented Generation (RAG)

🔌 Compatible Software

Ollama

📦 Repository Contents

GGUF Model
Model Configuration
Tokenizer
README
License

⚠ Disclaimer

UniFriendAI is intended for educational purposes only.

Although fine-tuned for undergraduate Information Technology education, the model may occasionally generate inaccurate or outdated information.

Always verify important academic content using official university lecture notes, textbooks, and trusted educational resources.

❤️ Mission

Our mission is to make high-quality AI tutoring accessible to every Information Technology student by providing an intelligent, affordable, and locally deployable educational assistant.

Happy Learning! 🎓

👨‍💻 Developer

UniFriendAI was independently developed and fine-tuned by Jehan Kandy to support undergraduate Information Technology education through accessible and locally deployable artificial intelligence.

🌐 Connect

GitHub: https://github.com/BackendExpert
Hugging Face: https://huggingface.co/jehanweerasuriya
LinkedIn: https://www.linkedin.com/in/jehanweerasuriya/
Website: https://blackalphalabs.com/

🤝 Contributions

Contributions, feature requests, bug reports, and educational collaborations are welcome.

If UniFriendAI has been helpful in your learning journey, consider ⭐ starring the repository and sharing it with fellow students.

Developed with ❤️ by Jehan Weerasuriya

Downloads last month: 32

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for jehanweerasuriya/UniFriendAI

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Quantized

(271)

this model