Instructions to use MayensGuds/SambaLingo-Arabic-Chat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MayensGuds/SambaLingo-Arabic-Chat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MayensGuds/SambaLingo-Arabic-Chat-GGUF",
	filename="sambalingo-arabic-chat.Q4_K_M.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 MayensGuds/SambaLingo-Arabic-Chat-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MayensGuds/SambaLingo-Arabic-Chat-GGUF: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 MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MayensGuds/SambaLingo-Arabic-Chat-GGUF: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 MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M

Use Docker

docker model run hf.co/MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use MayensGuds/SambaLingo-Arabic-Chat-GGUF with Ollama:
```
ollama run hf.co/MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M
```

Unsloth Studio new

How to use MayensGuds/SambaLingo-Arabic-Chat-GGUF 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 MayensGuds/SambaLingo-Arabic-Chat-GGUF 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 MayensGuds/SambaLingo-Arabic-Chat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MayensGuds/SambaLingo-Arabic-Chat-GGUF to start chatting

Docker Model Runner
How to use MayensGuds/SambaLingo-Arabic-Chat-GGUF with Docker Model Runner:
```
docker model run hf.co/MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M
```

Lemonade

How to use MayensGuds/SambaLingo-Arabic-Chat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MayensGuds/SambaLingo-Arabic-Chat-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SambaLingo-Arabic-Chat-GGUF-Q4_K_M

List all available models

lemonade list

This is a qunatization of the sambaLingo LLama based arabic chat model

الموديل هذا تم عمل تكميم له, بمعنى انه يمكن تشغيله على اجهزة اللابتوب او الكمبيوترات العادية

لو تمتلك حوالي 8 جيجا بايت من الرام سوف تستطيع استخدام هذا الموديل

تجربة النموذج:

حدود النموذج:

الموديل محدود بالكلام العربي ولا يستطيع فهم اللهجات الغير الفصحى
النموذج مبني على Llama2 لاما2 تم تدريبها على كلام باللغة الانجليزية وبعض اللغات الاخرى ولكن معظم مجموعة البيانات كانت لغات غير عربية بالتالي يوجد تحيز كامل في النموذج

لو تمتلك اهتمام ببناء نموذج محادثات عربي او تمتلك داتا سيت باللهجات العربية تواصل معي لكي نتساعد على بناء اول وايفو عربي :3

شكرا!

Downloads last month: 29

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

Inference Providers NEW

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