نموذج صقر بحجم 50 مليون لتوليد البيانات بالعربي يعمل علي CPU
ماهو نموذج Sakr صقر المخصص لتوليد البيانات باللغة العربية ومدرب علي حوالي 66 مليون صفحة من fine-web dataset يعمل بسرعه فائقة ونتائج متوسطة. شرح تفصيلي.
note
مقالات وتجارب وملاحظات حول note.
ماهي Likve Kit مقدمة سريعة
هي مشروع مفتوح المصدر لبناء وكلاء ذكاء إصطناعي تتعامل مع الصوت و الصورة بشكل لحظي وتشمل كل ما يحتاجه المبرمج
فوائد و أضرار عمل قناة يوتيوب لمشاركة المعرفة
بشارك خواطر تجربة إنشاء قناة لمشاركة المعارف في تخصصي وهو الذكاء الإصطناعي والبرمجة في عام ملئ بالتشتت والسطحية في نشر المعرفة.
Using Dinov3 Search to Identify Fonts in Historical Arabic Books
Building OCR for historical Arabic manuscripts is hard when you don't know what fonts the text resembles. I built a simple image similarity pipeline using DINOv3 and Qdrant to match page scans against 300 Arabic fonts — and found one font d
Latest TTS Architecture and differences | 2026
Gallery of Popular TTS Architecture and Papers, Pros and Cons and unique ideas from them, quickly explained.
Fine-Tuning Gemma 3 for Arabic Tool Calling: A No-RAG Approach
How we taught a 1B parameter Gemma 3 model to use grep for Arabic information retrieval, avoiding embeddings and RAG systems.
Kareem CV of Failures 'Rejections build Career'
A quick summary of My personal failure and why you should write also a cv of failures to help you track the problems you create over time
My Journey building a PC for AI Research in Egypt
A personal journey of building a high-performance PC for AI research in Egypt, covering hardware choices, cost comparisons with cloud providers, and the unique challenges of building locally.
Hacker AI Engineer Interview 2026 Example
HackerRank AI engineer interview review 2026. prompt engineering, SQL, and RAG coding challenges that test memorization over real-world AI skills.
LiteRT and Qualcomm AI Hub: On-Device ML Without the Cloud
A practical guide for ML engineers on converting PyTorch models to LiteRT, benchmarking on real Android devices via ADB, and when to use Qualcomm AI Hub for NPU compilation.
Vector Databases - O'reilly By Nitin Borwankar
Review of a new book about Vector database from O'reilly
HyperRun + ColGrep: A Self-Hosted Alternative to RunLLM
HyperRun is an open-source, self-hosted alternative to RunLLM. Add an AI-powered "Ask AI" chat widget to any docs site using ColGrep semantic code search, Lisette LLM orchestration, and FastHTML. Supports BYOK, multi-provider, and embeds wi
HyperRun Deep Dive: Streaming Chat with FastHTML, HTMX, and SSE
How I built a real-time AI chat widget with zero React, zero WebSockets, and almost zero custom JavaScript. A deep dive into FastHTML's server-rendered approach — SSE streaming, DaisyUI modals with checkbox toggles, OOB swaps, session-based
Building SEO RAT: A Free, Open-Source SEO Tool
Why I'm building SEO RAT — an open-source SEO tool focused on real gains from Google Search Console, smart visualizations, and AI-powered keyword analysis.
OpenCode: Why It's Different and How to Use It with Python
Learn how OpenCode works as programmable AI coding infrastructure. Built in TypeScript, controlled with Python — covering agents, skills, PLAN.md, and MLflow integration.
Super Productivity Review: Best Free Todo App (2026)
A detailed review of Super Productivity, the free open source todo app. Explore how I use it for managing AI research, development tasks, and daily productivity.
Tarteel & Muaalem El Quran: Optimizing Quranic AI Part 2
Discover how I optimized the Muaalem El Quran model using TensorRT and ONNX. A deep dive into Quranic speech recognition and my journey with Tarteel AI.
OnePlus Pad 3 Review (2025) - Researcher Review
OnePlus Pad 3 revie: Snapdragon 8 Elite, 13.2-inch 3.4K 144Hz display, 12,140mAh battery, 80W charging. Is it the best Android tablet for productivity in 2025?
Huawei FreeBuds 7i Review: Worth Upgrading from 5i?
Review of Huawei FreeBuds 7i after 20 days, comparing call quality, ANC, battery, specs, and if these wireless earbuds are worth upgrading from 5i.
From $32,000 to $0 with Small Models and CTranslate2
From $32k to $0 translating with small models and CTranslate2; includes compute_type int8_float16, quantization 4-bit, and 4-6x speed gains.
My Dream Job at Tarteel: ML Engineer's Journey
Sharing my thoughts about my dream to work at Tarteel on Quran as Machine learning Engineer
Math for AI Roadmap: Concepts & Course Prep
Explore my roadmap for mastering the mathematical foundations of AI, covering linear algebra, calculus, and probability for machine learning research.
Federated Learning: Definition, Examples & Benefits
Learn what Federated Learning is, how it works with decentralized data, examples like Gboard, and why it's crucial for privacy and low-bandwidth training.
Google Ads Black Box: Suspension Recovery Dubai & Arabic Ads
How to handle Google Ads suspension, recovery tips (Dubai), and navigating the Google Ads black box for Arabic businesses.
Mastering Data Structures for Machine Learning Engineering
Data structures & algorithms for ML engineers: boost problem-solving, grasp complexity, and move beyond Jupyter.
Huawei Watch GT 4 Review – GPS & Sleep Tracking in India
Long-term Huawei Watch GT4 review covering GPS accuracy, sleep tracking, language support (Arabic, Chinese, Thai), and usage in India.
MSI Gaming Laptop Review: My 4-Year ML Workhorse 'Kobo'
MSI gaming laptop review from a machine-learning student: 4-year journey with 'Kobo' GTX 1660 Ti, Linux tweaks, battery & heat notes.
Huawei MatePad 11 Review: One Year Without Google Services
A detailed student review of the Huawei MatePad 11 after one year. Exploring life without Google services, app compatibility, and integration with Linux.
Huawei FreeBuds 5i Review: Best Budget ANC Earbuds?
Two-month Huawei FreeBuds 5i review covering ANC performance, sound, battery, Linux compatibility, and microphone/call quality.
MTEB Benchmark: Tasks, Datasets & nDCG@10 Explained
Overview of MTEB, covering 58 datasets across 8 tasks, benchmarking models and explaining the nDCG@10 retrieval metric.
tiny-gte: Efficient Transformer for Semantic Search
tiny-gte is a 45MB distilled transformer from gte-small that produces 384D embeddings for efficient semantic search and vector DBs.
Harvard CS197: AI Research Experiences & Deep Learning Guide
Review of Harvard CS197 (CS 197) AI Research Experiences: 21 lectures on deep-learning research, paper reading, and productivity.