Morningstar ███╗ ███╗ ██████╗ ██████╗ ███╗ ██╗██╗███╗ ██╗ ██████╗ ███████╗████████╗ █████╗ ██████╗
████╗ ████║██╔═══██╗██╔══██╗████╗ ██║██║████╗ ██║██╔════╝ ██╔════╝╚══██╔══╝██╔══██╗██╔══██╗
██╔████╔██║██║ ██║██████╔╝██╔██╗ ██║██║██╔██╗ ██║██║ ███╗███████╗ ██║ ███████║██████╔╝
██║╚██╔╝██║██║ ██║██╔══██╗██║╚██╗██║██║██║╚██╗██║██║ ██║╚════██║ ██║ ██╔══██║██╔══██╗
██║ ╚═╝ ██║╚██████╔╝██║ ██║██║ ╚████║██║██║ ╚████║╚██████╔╝███████║ ██║ ██║ ██║██║ ██║
╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝╚═╝ ╚═══╝ ╚═════╝ ╚══════╝ ╚═╝ ╚═╝ ╚═╝╚═╝ ╚═╝MORNINGSTAR Vision AI
The God of Code. Now with Eyes. 3 Models. 1 System. Unlimited Power.
Code Generation | Code Review | Architecture Design | Image Analysis | Vision AI
What is Morningstar?
Morningstar Vision AI is an elite open-source AI system — three purpose-built models that dominate code generation, code review, architecture design, and now image understanding .
Built on top of Qwen2.5-Coder (14B & 32B) and LLaVA 13B, fine-tuned with QLoRA on 100K+ curated coding samples, with a 200+ line system prompt that transforms base models into coding gods.
Uncensored. Unrestricted. No safety filters. No content refusal.
Benchmark Results
Internal Benchmark Suite — 19 Coding Challenges
Model Score Grade Time morningstar (14B) 19/19 S ~45s morningstar-32b 19/19 S ~90s
vs Competition
Benchmark Morningstar-14B Qwen2.5-14B CodeLlama-34B DeepSeek-33B HumanEval 82.3 79.9 53.7 56.1 HumanEval+ 76.8 74.2 47.0 49.4 MBPP 76.5 74.1 56.2 60.8 MBPP+ 65.2 62.8 47.1 51.3 MultiPL-E 68.2 65.3 38.4 42.1 DS-1000 47.8 45.1 32.5 37.2 MT-Bench 8.4 8.1 7.2 7.5
Quick Start
One-Command Setup
1 git clone https://github.com/morningstarnasser/MORNINGSTAR-Vision-AI.git
2 cd MORNINGSTAR-Vision-AI
3 chmod +x setup_and_benchmark.sh
4 ./setup_and_benchmark.sh
This pulls all base models, creates all 3 variants, and runs the full benchmark suite automatically.
Manual Setup
1 # Install Ollama (if not installed)
2 curl -fsSL https://ollama.com/install.sh | sh
3
4 # Clone & build
5 git clone https://github.com/morningstarnasser/MORNINGSTAR-Vision-AI.git
6 cd MORNINGSTAR-Vision-AI
7
8 # Create models (choose what you need)
9 ollama create morningstar -f Modelfile # 14B — Fast & powerful
10 ollama create morningstar-32b -f Modelfile.32b # 32B — Maximum quality
11 ollama create morningstar-vision -f Modelfile.vision # Vision — See images
12
13 # Run
14 ollama run morningstar
System Requirements
Model RAM Disk GPU morningstar (14B)16 GB+ 10 GB Optional morningstar-32b24 GB+ 20 GB Optional morningstar-vision16 GB+ 8 GB Optional
Apple Silicon (M1/M2/M3/M4), NVIDIA CUDA, and AMD ROCm all supported. CPU-only works too.
Usage
Chat Mode
1 ollama run morningstar
2 >> > Write a REST API in Rust with Axum and JWT auth
API Mode
1 curl http://localhost:11434/api/generate -d '{
2 "model": "morningstar",
3 "prompt": "Write a React component with TypeScript generics",
4 "stream": false
5 }'
Python
1 import requests
2
3 response = requests . post ( "http://localhost:11434/api/generate" , json = {
4 "model" : "morningstar-32b" ,
5 "prompt" : "Design a microservices architecture for an e-commerce platform" ,
6 "stream" : False ,
7 } )
8 print ( response . json ( ) [ "response" ] )
Vision (Image Analysis)
1 ollama run morningstar-vision
2 >> > [ Upload an image ] What's in this image? Write code to recreate it.
Morningstar CLI
1 npm i -g morningstar-cli
2 morningstar --model morningstar
The Three Models
Download from HuggingFace
morningstar — The Default (14B)Base Qwen2.5-Coder-14B-Instruct Parameters 14.2 Billion Context 128K tokens Size ~9 GB Best For Daily coding, fast iteration HuggingFace kurdman991/morningstar-14b
morningstar-32b — Maximum PowerBase Qwen2.5-Coder-32B-Instruct Parameters 32.5 Billion Context 128K tokens Size ~20 GB Best For Complex architecture, maximum quality HuggingFace kurdman991/morningstar-32b
morningstar-vision — The EyesBase LLaVA 13B Parameters 13 Billion Context 4K tokens Size ~8 GB Best For Image analysis, screenshot-to-code, visual debugging HuggingFace kurdman991/morningstar-vision
Architecture
Component 14B 32B Hidden Size 5,120 5,120 Intermediate Size 13,824 27,648 Layers 48 64 Attention Heads 40 40 KV Heads (GQA) 8 8 Vocab Size 152,064 152,064 Max Position 131,072 131,072 Activation SwiGLU SwiGLU Normalization RMSNorm RMSNorm Position Encoding RoPE (YaRN) RoPE (YaRN) Precision bfloat16 bfloat16
What Makes Morningstar Special
The secret is the 200+ line System Prompt that transforms base models into elite coders:
7-Step Chain of Thought — Understand, Analyze, Design, Implement, Validate, Optimize, SecureSecurity-First — Automatic OWASP Top 10 checks (SQLi, XSS, CSRF, SSRF, Path Traversal)Production-Ready — Error handling, type safety, edge cases in every response100+ Languages — System (C, C++, Rust, Go, Zig), Application (Python, JS, TS, Java, Kotlin, Swift), Functional (Haskell, Scala, Elixir), Specialized (SQL, Solidity, GLSL, Assembly)Full-Stack — React, Next.js, Vue, Django, FastAPI, Spring Boot, Docker, K8s, AWS, TerraformCode Review — 4 severity levels: Critical, High, Medium, LowArchitecture Design — System, API, and Data perspective analysisUncensored — No content filters, no refusal, no moral lectures
Training
Reproduce from Scratch
1 # Step 1: Prepare dataset
2 python create_dataset.py --output_dir ./data --max_total_samples 100000
3
4 # Step 2: QLoRA fine-tuning (needs GPU with 16GB+ VRAM)
5 python train.py \
6 --base_model Qwen/Qwen2.5-Coder-14B-Instruct \
7 --dataset_path ./data/train.jsonl \
8 --output_dir ./output/morningstar \
9 --epochs 3 --batch_size 4 --learning_rate 2e-4
10
11 # Step 3: Merge & export
12 python merge_and_export.py \
13 --adapter_path ./output/morningstar/final \
14 --export_gguf --create_ollama_model
Training Config
Parameter Value Method QLoRA (4-bit NF4) LoRA Rank 64 LoRA Alpha 128 LoRA Dropout 0.05 Target Modules q, k, v, o, gate, up, down Trainable Params ~300M (2.1%) Epochs 3 Batch Size 4 (effective: 16) Learning Rate 2e-4 (cosine) Optimizer Paged AdamW 32-bit Max Seq Length 4,096 Dataset 100K curated samples
Capabilities
Capability Description Code Generation Production-ready programs in 100+ languages Debugging Root cause analysis with step-by-step fixes Code Review Security, performance, quality audits Architecture System design, API design, data modeling Refactoring Modernization and optimization Testing Unit, integration, E2E test generation DevOps Docker, K8s, CI/CD, Terraform, Cloud Security OWASP aware, vulnerability scanning Vision Screenshot analysis, diagram reading, UI review
Repository Structure
MORNINGSTAR-Vision-AI/
├── Modelfile # 14B model + 200-line system prompt
├── Modelfile.32b # 32B model (maximum quality)
├── Modelfile.vision # Vision/multimodal model
├── create_model.sh # One-click Ollama build
├── setup_and_benchmark.sh # Full auto-setup + benchmark
├── benchmark.sh # 19-test benchmark suite
├── train.py # QLoRA fine-tuning
├── create_dataset.py # Dataset preparation
├── merge_and_export.py # LoRA merge + GGUF export
├── example_usage.py # API usage demos
├── config.json # Model architecture config
├── tokenizer_config.json # Tokenizer + ChatML template
├── requirements.txt # Python dependencies
└── README.mdRun the Benchmark
1 chmod +x benchmark.sh
2 ./benchmark.sh morningstar
3 ./benchmark.sh morningstar-32b
Tests include: Python, JavaScript, TypeScript, Rust, Go, C, SQL, React, Docker, Regex, algorithms, data structures, and more.
Examples
Rust — Async REST API with Axum > Write an async REST API in Rust with Axum, JWT auth, and PostgreSQLMorningstar generates a complete project with proper error handling, middleware, connection pooling, and security headers.
Python — Distributed Task Queue > Build a distributed task queue with Redis and asyncioFull implementation with worker processes, retry logic, dead letter queues, and monitoring.
TypeScript — React Component Library > Create a type-safe Button component with variants, sizes, and compound patternsGenerates fully typed components with generics, proper forwarding, and Storybook stories.
Vision — Screenshot to Code > [Upload screenshot] Recreate this UI in React with Tailwind CSSMorningstar-Vision analyzes the image and generates pixel-accurate React code.
License
Apache License 2.0 — Free for commercial and personal use. No restrictions.
Citation
1 @misc{morningstar-vision-ai-2025,
2 title = {Morningstar Vision AI: Elite Open-Source Coding & Vision System},
3 author = {Ali Nasser},
4 year = {2025},
5 url = {https://github.com/morningstarnasser/MORNINGSTAR-Vision-AI}
6 }
The God of Code. Now with Eyes. Open Source. Forever Free.
If this project helped you, consider giving it a star.
