Instructions to use eltay89/ALLaM-7B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use eltay89/ALLaM-7B-Instruct-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="eltay89/ALLaM-7B-Instruct-GGUF", filename="ALLaM-7B-Instruct-Q2_K.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use eltay89/ALLaM-7B-Instruct-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf eltay89/ALLaM-7B-Instruct-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 eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf eltay89/ALLaM-7B-Instruct-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 eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf eltay89/ALLaM-7B-Instruct-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 eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M
Use Docker
docker model run hf.co/eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use eltay89/ALLaM-7B-Instruct-GGUF with Ollama:
ollama run hf.co/eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M
- Unsloth Studio
How to use eltay89/ALLaM-7B-Instruct-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 eltay89/ALLaM-7B-Instruct-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 eltay89/ALLaM-7B-Instruct-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for eltay89/ALLaM-7B-Instruct-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use eltay89/ALLaM-7B-Instruct-GGUF with Docker Model Runner:
docker model run hf.co/eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M
- Lemonade
How to use eltay89/ALLaM-7B-Instruct-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull eltay89/ALLaM-7B-Instruct-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.ALLaM-7B-Instruct-GGUF-Q4_K_M
List all available models
lemonade list
๐ฆ ALLaM-7B-Instruct-GGUF
This repository provides quantized GGUF versions of ALLaM-7B-Instruct, optimized for efficient inference using llama.cpp.
โ ๏ธ Acknowledgment
The original model was developed by ALLaM-AI and is available here:
๐ ALLaM-7B-Instruct-Preview
This repository only provides quantized versions for improved performance on different hardware.
โจ Overview
ALLaM-7B-Instruct is an Arabic-centric instruction-tuned model based on Metaโs LLaMA architecture, designed for natural language understanding and generation in Arabic.
๐ Whatโs New?
โ
GGUF Format โ Optimized for llama.cpp
โ
Multiple Quantization Levels โ Balance between precision and efficiency
โ
Run on CPUs & Low-Resource Devices โ No need for high-end GPUs!
๐ Available Model Quantizations
| Model Variant | Precision | Size | Best For |
|---|---|---|---|
ALLaM-7B-Instruct-f16.gguf |
FP16 | Large | High-precision tasks |
ALLaM-7B-Instruct-Q8_0.gguf |
8-bit | Medium | Balanced quality & speed |
ALLaM-7B-Instruct-Q6_K.gguf |
6-bit | Small | Good trade-off |
ALLaM-7B-Instruct-Q5_0.gguf |
5-bit | Small | Alternative quantization |
ALLaM-7B-Instruct-Q5_K_M.gguf |
5-bit | Smaller | Fast inference |
ALLaM-7B-Instruct-Q4_0.gguf |
4-bit | Very Small | Legacy format |
ALLaM-7B-Instruct-Q4_K_M.gguf |
4-bit | Very Small | Low-memory devices |
ALLaM-7B-Instruct-Q2_K.gguf |
2-bit | Smallest | Extreme efficiency |
๐ Installation & Setup
1๏ธโฃ Install llama.cpp
Clone and build llama.cpp:
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make
2๏ธโฃ Download the Model
Choose and download a .gguf file from this repository.
3๏ธโฃ Run Inference
Use llama.cpp to generate responses:
./main -m ALLaM-7B-Instruct-Q4_0.gguf -p "ููู ุฃุฌูุฒ ููุจ ุดุงููุ"
Expected Output:
ูุชุญุถูุฑ ููุจ ุดุงูุ ุงุบูู ุงูู
ุงุกุ ุถุน ุงูุดุงู ูู ุงูููุจุ ูุงุณูุจ ุงูู
ุงุก ุงูุณุงุฎู ูููู. ุงุชุฑูู ูุฏูุงุฆู ุซู
ุงุณุชู
ุชุน ุจู
ุฐุงูู!
๐ Benchmarks & Performance
| Quantization Format | Model Size | CPU (Tokens/sec) | GPU (Tokens/sec) |
|---|---|---|---|
| FP16 | Large | ~2 | ~15 |
| Q8_0 | Medium | ~4 | ~30 |
| Q6_K | Smaller | ~6 | ~40 |
| Q5_0 | Small | ~7 | ~42 |
| Q5_K_M | Smaller | ~8 | ~45 |
| Q4_0 | Very Small | ~9 | ~48 |
| Q4_K_M | Very Small | ~10 | ~50 |
| Q2_K | Smallest | ~12 | ~55 |
Performance may vary based on hardware and configuration.
๐ License
This model follows the ALLaM-AI license. Refer to their Hugging Face repository for details.
โค๏ธ Acknowledgments
- ALLaM-AI for developing the original ALLaM-7B-Instruct model.
- llama.cpp by ggerganov for optimized inference.
โญ Contributions & Feedback
If you find this quantized model useful, feel free to contribute, provide feedback, or share your results!
- Downloads last month
- 106
2-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for eltay89/ALLaM-7B-Instruct-GGUF
Base model
humain-ai/ALLaM-7B-Instruct-preview