Instructions to use aelgendy/QModel 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 aelgendy/QModel 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 aelgendy/QModel:Q8_0 # Run inference directly in the terminal: llama cli -hf aelgendy/QModel:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf aelgendy/QModel:Q8_0 # Run inference directly in the terminal: llama cli -hf aelgendy/QModel:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf aelgendy/QModel:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf aelgendy/QModel:Q8_0
Use Docker
docker model run hf.co/aelgendy/QModel:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use aelgendy/QModel with Ollama:
ollama run hf.co/aelgendy/QModel:Q8_0
- Unsloth Desktop
- Pi
How to use aelgendy/QModel with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf aelgendy/QModel:Q8_0
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "aelgendy/QModel:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use aelgendy/QModel with Docker Model Runner:
docker model run hf.co/aelgendy/QModel:Q8_0
- Lemonade
How to use aelgendy/QModel with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull aelgendy/QModel:Q8_0
Run and chat with the model
lemonade run user.QModel-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use aelgendy/QModel with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf aelgendy/QModel:Q8_0
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://127.0.0.1:9931/v1 hermes config set model.default aelgendy/QModel:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use aelgendy/QModel with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf aelgendy/QModel:Q8_0
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://127.0.0.1:9931/v1 \ --custom-model-id "aelgendy/QModel:Q8_0" \ --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"
Add interactive chat.py CLI tool with FAISS
Browse files- app/state.py +3 -0
- chat.py +78 -0
app/state.py
CHANGED
|
@@ -331,6 +331,9 @@ def _verify_references(answer: str, results: list) -> str:
|
|
| 331 |
# Check and correct Quranic URLs to match authoritative retrieved reference
|
| 332 |
if len(valid_refs) == 1:
|
| 333 |
correct_sn, correct_vn = next(iter(valid_refs))
|
|
|
|
|
|
|
|
|
|
| 334 |
|
| 335 |
def _check_surah_url(m: re.Match) -> str:
|
| 336 |
vn, sn = int(m.group(1)), int(m.group(2))
|
|
|
|
| 331 |
# Check and correct Quranic URLs to match authoritative retrieved reference
|
| 332 |
if len(valid_refs) == 1:
|
| 333 |
correct_sn, correct_vn = next(iter(valid_refs))
|
| 334 |
+
actual_surah_url = f"https://surahquran.com/aya-{correct_vn}-sora-{correct_sn}.html"
|
| 335 |
+
actual_tafsir_url = f"https://quran.ksu.edu.sa/tafseer/qortobi/sura{correct_sn}-aya{correct_vn}.html"
|
| 336 |
+
answer = answer.replace("{surah_url}", actual_surah_url).replace("{tafsir_url}", actual_tafsir_url)
|
| 337 |
|
| 338 |
def _check_surah_url(m: re.Match) -> str:
|
| 339 |
vn, sn = int(m.group(1)), int(m.group(2))
|
chat.py
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""
|
| 3 |
+
Interactive CLI for QModel (FAISS + BM25 + Ollama/GGUF).
|
| 4 |
+
Run directly in your terminal to query the full Islamic RAG system.
|
| 5 |
+
"""
|
| 6 |
+
|
| 7 |
+
import os
|
| 8 |
+
import sys
|
| 9 |
+
import json
|
| 10 |
+
import asyncio
|
| 11 |
+
import logging
|
| 12 |
+
|
| 13 |
+
# Suppress verbose warnings
|
| 14 |
+
os.environ.setdefault("KMP_DUPLICATE_LIB_OK", "TRUE")
|
| 15 |
+
os.environ.setdefault("OMP_NUM_THREADS", "1")
|
| 16 |
+
logging.basicConfig(level=logging.WARNING)
|
| 17 |
+
|
| 18 |
+
from app.config import cfg
|
| 19 |
+
from app.state import state, _build_lookup_tables, run_rag_pipeline
|
| 20 |
+
from app.llm import get_llm_provider
|
| 21 |
+
from sentence_transformers import SentenceTransformer
|
| 22 |
+
import faiss
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
async def init_qmodel():
|
| 26 |
+
print("⏳ Loading QModel Islamic RAG System...")
|
| 27 |
+
print(f" • Loading metadata: {cfg.METADATA_FILE}")
|
| 28 |
+
with open(cfg.METADATA_FILE, "r", encoding="utf-8") as f:
|
| 29 |
+
state.dataset = json.load(f)
|
| 30 |
+
|
| 31 |
+
print(" • Building BM25 & scripture lookup tables...")
|
| 32 |
+
_build_lookup_tables(state.dataset)
|
| 33 |
+
|
| 34 |
+
print(f" • Loading dense embeddings ({cfg.EMBED_MODEL})...")
|
| 35 |
+
state.embed_model = SentenceTransformer(cfg.EMBED_MODEL)
|
| 36 |
+
|
| 37 |
+
print(f" • Loading FAISS vector index ({cfg.FAISS_INDEX})...")
|
| 38 |
+
state.faiss_index = faiss.read_index(cfg.FAISS_INDEX)
|
| 39 |
+
|
| 40 |
+
print(f" • Connecting to LLM backend ({cfg.LLM_BACKEND})...")
|
| 41 |
+
state.llm = get_llm_provider()
|
| 42 |
+
state.ready = True
|
| 43 |
+
print("✅ QModel is ready!\n" + "=" * 60)
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
async def main():
|
| 47 |
+
await init_qmodel()
|
| 48 |
+
|
| 49 |
+
print("🕌 Sheikh QModel — Islamic Knowledge Assistant (Quran, Tafsir, Hadith, Fatwa)")
|
| 50 |
+
print("Type your question below (or 'exit' / 'quit' to exit):\n")
|
| 51 |
+
|
| 52 |
+
while True:
|
| 53 |
+
try:
|
| 54 |
+
query = input("Q: ").strip()
|
| 55 |
+
except (EOFError, KeyboardInterrupt):
|
| 56 |
+
print("\nوداعاً — مع السلامة.")
|
| 57 |
+
break
|
| 58 |
+
|
| 59 |
+
if not query:
|
| 60 |
+
continue
|
| 61 |
+
if query.lower() in ("exit", "quit", "q"):
|
| 62 |
+
print("مع السلامة.")
|
| 63 |
+
break
|
| 64 |
+
|
| 65 |
+
print("\n⏳ جاري البحث في الفهرس والتحقق من النصوص...")
|
| 66 |
+
try:
|
| 67 |
+
res = await run_rag_pipeline(query)
|
| 68 |
+
print("\n" + res["answer"] + "\n")
|
| 69 |
+
print("-" * 60)
|
| 70 |
+
except Exception as exc:
|
| 71 |
+
print(f"❌ حدث خطأ: {exc}\n")
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
if __name__ == "__main__":
|
| 75 |
+
try:
|
| 76 |
+
asyncio.run(main())
|
| 77 |
+
except KeyboardInterrupt:
|
| 78 |
+
pass
|