Instructions to use HaifaAlsalem/shamel-service-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HaifaAlsalem/shamel-service-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HaifaAlsalem/shamel-service-v1",
	filename="model-q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use HaifaAlsalem/shamel-service-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HaifaAlsalem/shamel-service-v1:Q8_0
# Run inference directly in the terminal:
llama-cli -hf HaifaAlsalem/shamel-service-v1:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HaifaAlsalem/shamel-service-v1:Q8_0
# Run inference directly in the terminal:
llama-cli -hf HaifaAlsalem/shamel-service-v1:Q8_0

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 HaifaAlsalem/shamel-service-v1:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf HaifaAlsalem/shamel-service-v1:Q8_0

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 HaifaAlsalem/shamel-service-v1:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HaifaAlsalem/shamel-service-v1:Q8_0

Use Docker

docker model run hf.co/HaifaAlsalem/shamel-service-v1:Q8_0

LM Studio
Jan
Ollama
How to use HaifaAlsalem/shamel-service-v1 with Ollama:
```
ollama run hf.co/HaifaAlsalem/shamel-service-v1:Q8_0
```

Unsloth Studio new

How to use HaifaAlsalem/shamel-service-v1 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 HaifaAlsalem/shamel-service-v1 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 HaifaAlsalem/shamel-service-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HaifaAlsalem/shamel-service-v1 to start chatting

Docker Model Runner
How to use HaifaAlsalem/shamel-service-v1 with Docker Model Runner:
```
docker model run hf.co/HaifaAlsalem/shamel-service-v1:Q8_0
```

Lemonade

How to use HaifaAlsalem/shamel-service-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HaifaAlsalem/shamel-service-v1:Q8_0

Run and chat with the model

lemonade run user.shamel-service-v1-Q8_0

List all available models

lemonade list

Shamel Service — v1

On-device Arabic assistant for the Tawakkalna app, fine-tuned from unsloth/gemma-4-e2b-it.

Training details

Base model: unsloth/gemma-4-e2b-it @ main
Training data: HaifaAlsalem/shamel-service-data @ main
Method: LoRA SFT via Unsloth + TRL
Hyperparameters: lr=5e-05, epochs=2, batch=16, lora_r=16

Files

model.safetensors — merged fp16 weights
*.gguf — GGUF quantization for on-device deployment (LM Studio, llama.cpp)
Tokenizer with baked SHAMEL_SYSTEM prompt in chat_template

Usage

LM Studio:

Download the .gguf file
Place in LM Studio's models folder
Load and chat — SHAMEL_SYSTEM auto-injects via baked chat_template

Python (transformers):

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("HaifaAlsalem/shamel-service-v1", revision="v1")
model = AutoModelForCausalLM.from_pretrained("HaifaAlsalem/shamel-service-v1", revision="v1")

Downloads last month: 81

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support