Instructions to use theBOrg32/Syrian_qwen_mobile_version with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use theBOrg32/Syrian_qwen_mobile_version 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 theBOrg32/Syrian_qwen_mobile_version # Run inference directly in the terminal: llama cli -hf theBOrg32/Syrian_qwen_mobile_version
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf theBOrg32/Syrian_qwen_mobile_version # Run inference directly in the terminal: llama cli -hf theBOrg32/Syrian_qwen_mobile_version
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 theBOrg32/Syrian_qwen_mobile_version # Run inference directly in the terminal: ./llama-cli -hf theBOrg32/Syrian_qwen_mobile_version
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 theBOrg32/Syrian_qwen_mobile_version # Run inference directly in the terminal: ./build/bin/llama-cli -hf theBOrg32/Syrian_qwen_mobile_version
Use Docker
docker model run hf.co/theBOrg32/Syrian_qwen_mobile_version
- LM Studio
- Jan
- Ollama
How to use theBOrg32/Syrian_qwen_mobile_version with Ollama:
ollama run hf.co/theBOrg32/Syrian_qwen_mobile_version
- Unsloth Desktop
- Pi
How to use theBOrg32/Syrian_qwen_mobile_version with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf theBOrg32/Syrian_qwen_mobile_version
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "theBOrg32/Syrian_qwen_mobile_version" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use theBOrg32/Syrian_qwen_mobile_version with Docker Model Runner:
docker model run hf.co/theBOrg32/Syrian_qwen_mobile_version
- Lemonade
How to use theBOrg32/Syrian_qwen_mobile_version with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull theBOrg32/Syrian_qwen_mobile_version
Run and chat with the model
lemonade run user.Syrian_qwen_mobile_version-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use theBOrg32/Syrian_qwen_mobile_version with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf theBOrg32/Syrian_qwen_mobile_version
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 theBOrg32/Syrian_qwen_mobile_version
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use theBOrg32/Syrian_qwen_mobile_version with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf theBOrg32/Syrian_qwen_mobile_version
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 "theBOrg32/Syrian_qwen_mobile_version" \ --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"
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,96 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-sa-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-sa-4.0
|
| 3 |
+
library_name: gguf
|
| 4 |
+
tags:
|
| 5 |
+
- gguf
|
| 6 |
+
- syrian-arabic
|
| 7 |
+
- dialect
|
| 8 |
+
- qwen
|
| 9 |
+
- llama-cpp
|
| 10 |
+
- mobile-ai
|
| 11 |
+
- pocketpal
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# πΈπΎ Syrian_Qwen-3.5-GGUF: Syrian Dialect LLM for Edge & Mobile
|
| 15 |
+
|
| 16 |
+
<p align="center">
|
| 17 |
+
<img src="https://img.shields.io/badge/License-CC--BY--SA--4.0-green.svg" alt="License">
|
| 18 |
+
<img src="https://img.shields.io/badge/Language-Arabic_(Syrian_Dialect)-red.svg" alt="Language">
|
| 19 |
+
<img src="https://img.shields.io/badge/Format-GGUF-purple.svg" alt="Format">
|
| 20 |
+
<img src="https://img.shields.io/badge/Compatible-PocketPal__APK-orange.svg" alt="PocketPal">
|
| 21 |
+
</p>
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
## π Introduction
|
| 26 |
+
|
| 27 |
+
**Run Syrian Dialect AI anywhere β on your phone, tablet, or edge device.**
|
| 28 |
+
|
| 29 |
+
We are proud to present **Syrian_Qwen-3.5-GGUF**, the quantized, portable version of the **first Large Language Model fine-tuned specifically for the Syrian Arabic Dialect**.
|
| 30 |
+
|
| 31 |
+
Built on **Qwen 3.5** and converted to the **GGUF format**, this model brings authentic Syrian Arabic understanding to resource-constrained environments β no cloud required, no data leaving your device.
|
| 32 |
+
|
| 33 |
+
### π Key Features
|
| 34 |
+
* π£οΈ **Native Syrian Dialect:** Trained on colloquial Syrian data, not just Modern Standard Arabic.
|
| 35 |
+
* π± **PocketPal Ready:** Optimized for seamless integration with PocketPal APK on Android.
|
| 36 |
+
* β‘ **Efficient Inference:** Powered by `llama.cpp` backend for fast, low-memory CPU execution.
|
| 37 |
+
* π **Open & Shareable:** CC-BY-SA-4.0 licensed to foster community growth.
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
## π± How to Run on Mobile with PocketPal APK
|
| 42 |
+
|
| 43 |
+
π₯ **Video Tutorial: Setting Up Syrian_Qwen-3.5 on PocketPal APK**
|
| 44 |
+
*[Video Placeholder β Coming Soon]*
|
| 45 |
+
*A step-by-step walkthrough will be uploaded here shortly showing:*
|
| 46 |
+
1. *Downloading PocketPal APK from the official source*
|
| 47 |
+
2. *Importing the Syrian_Qwen-3.5-GGUF model file*
|
| 48 |
+
3. *Configuring context length, temperature, and system prompt for Syrian dialect*
|
| 49 |
+
4. *Starting your first offline conversation in Syrian Arabic*
|
| 50 |
+
|
| 51 |
+
### Quick Setup Guide (Text)
|
| 52 |
+
1. Install **PocketPal APK** on your Android device.
|
| 53 |
+
2. Download this model (e.g., `syrian_qwen_3_5_4b_q4_k_m.gguf`) from the **Files** tab.
|
| 54 |
+
3. Open PocketPal β Models β **"+"** β **Load Model from local** β Select the downloaded `.gguf` file.
|
| 55 |
+
4. Start chatting fully offline, fully Syrian.
|
| 56 |
+
|
| 57 |
+
> β οΈ Ensure your device has at least 8GB RAM for Q4 quantizations. Close background apps for best performance.
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
## βοΈ License & Commercial Use
|
| 62 |
+
|
| 63 |
+
We believe in **open, shareable AI**. This model is released under **CC-BY-SA-4.0** to ensure derivatives remain open and community-driven.
|
| 64 |
+
|
| 65 |
+
### β
You Can:
|
| 66 |
+
- Use, modify, and distribute this model in **open-source projects** (with attribution).
|
| 67 |
+
- Use it commercially **if your derivative work remains open-source** under CC-BY-SA-4.0.
|
| 68 |
+
|
| 69 |
+
### π For Closed-Source / Proprietary Use:
|
| 70 |
+
If you plan to integrate this model (or a fine-tuned version) into a **closed product**, please contact us first:
|
| 71 |
+
|
| 72 |
+
π§ **Licensing Inquiries:** [info2@the-borg.ru](mailto:info2@the-borg.ru)
|
| 73 |
+
|
| 74 |
+
---
|
| 75 |
+
|
| 76 |
+
## π Credits & Acknowledgments
|
| 77 |
+
|
| 78 |
+
This project stands on the shoulders of incredible open-source work:
|
| 79 |
+
|
| 80 |
+
* π§ **Base Model:** [Qwen 3.5](https://huggingface.co/Qwen) by Alibaba Cloud
|
| 81 |
+
* βοΈ **GGUF Conversion & Runtime:** [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
| 82 |
+
* π± **Mobile Integration Reference:** [PocketPal APK](https://github.com/a-ghorbani/pocketpal-ai)
|
| 83 |
+
* π οΈ **Fine-Tuning & Alignment:** The Borg Organization
|
| 84 |
+
* π **Dataset:** Curated Syrian Dialect Corpus
|
| 85 |
+
|
| 86 |
+
### Citation
|
| 87 |
+
If you use **Syrian_Qwen-3.5-GGUF** in your work, please cite:
|
| 88 |
+
|
| 89 |
+
```bibtex
|
| 90 |
+
@misc{syrian_qwen_gguf_2026,
|
| 91 |
+
title={Syrian_Qwen-3.5-GGUF: Portable Syrian Dialect Large Language Model},
|
| 92 |
+
author={The Borg Organization},
|
| 93 |
+
year={2026},
|
| 94 |
+
howpublished={\url{https://huggingface.co/theBOrg32/Syrian_qwen_mobile_version}},
|
| 95 |
+
license={CC-BY-SA-4.0}
|
| 96 |
+
}
|