Instructions to use Sal-Wwh/EriFix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sal-Wwh/EriFix with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sal-Wwh/EriFix",
	filename="EriFix_Merged_Model.Q4_K_M.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 Sal-Wwh/EriFix with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sal-Wwh/EriFix:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sal-Wwh/EriFix:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sal-Wwh/EriFix:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sal-Wwh/EriFix: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 Sal-Wwh/EriFix:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sal-Wwh/EriFix: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 Sal-Wwh/EriFix:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sal-Wwh/EriFix:Q4_K_M

Use Docker

docker model run hf.co/Sal-Wwh/EriFix:Q4_K_M

LM Studio
Jan

vLLM

How to use Sal-Wwh/EriFix with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Sal-Wwh/EriFix:Q4_K_M

Ollama
How to use Sal-Wwh/EriFix with Ollama:
```
ollama run hf.co/Sal-Wwh/EriFix:Q4_K_M
```

Unsloth Studio

How to use Sal-Wwh/EriFix 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 Sal-Wwh/EriFix 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 Sal-Wwh/EriFix to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sal-Wwh/EriFix to start chatting

How to use Sal-Wwh/EriFix with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Sal-Wwh/EriFix: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": "Sal-Wwh/EriFix:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Sal-Wwh/EriFix with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Sal-Wwh/EriFix: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 Sal-Wwh/EriFix:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Sal-Wwh/EriFix with Docker Model Runner:
```
docker model run hf.co/Sal-Wwh/EriFix:Q4_K_M
```

Lemonade

How to use Sal-Wwh/EriFix with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sal-Wwh/EriFix:Q4_K_M

Run and chat with the model

lemonade run user.EriFix-Q4_K_M

List all available models

lemonade list

EriFix AI

EriFix AI is an offline troubleshooting and maintenance and Teaching assistant fine-tuned for Eritrean and general technology support.

The model is optimized for:

Android offline AI
smartphone troubleshooting
laptop and desktop support
Windows troubleshooting
router and networking problems
solar and inverter troubleshooting
printer/copier/scanner support
DIY repair guidance
maintenance assistance

Base Model

Qwen/Qwen2.5-1.5B-Instruct

Training Method

QLoRA fine-tuning
Unsloth optimization
4-bit training
GGUF export
Quantization: Q4_K_M

Supported Languages

English
Tigrinya
Mixed English + Tigrinya

Optimized For

Android phones
Offline AI assistants
llama.cpp
MLC Chat
PocketPal AI

Recommended RAM

Minimum:

4GB RAM

Recommended:

6GB+ RAM

Intended Use

EriFix AI is designed for:

troubleshooting guidance
maintenance support
educational technology assistance
offline technical support
Offline Technological Assistance

Limitations

EriFix AI may:

generate incorrect troubleshooting steps
hallucinate technical information
provide incomplete repair guidance

Because of Low Data all the above mentioned may or may not happen. Always verify critical repairs and electrical work carefully.

Developer

Developed by: Saleh Omer @Sal-Wwh salehomer200202@gmail.com +2917594507

Project: EriFix AI

Country: Eritrea

Downloads last month: 45

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit