Component 1: Project Setup (Windows + RTX 4060 8GB)
What This Component Does
- Creates a clean folder structure for the full coding-assistant project.
- Sets up a Python virtual environment.
- Installs all core dependencies needed across Components 2-10.
- Verifies that Python, PyTorch, CUDA visibility, and key libraries work.
Folder Structure Created
data/raw-> raw datasets you will provide laterdata/interim-> temporary cleaned datadata/processed-> training-ready tokenized datadata/external-> any third-party resourcessrc/tokenizer-> Component 2 code tokenizersrc/dataset_pipeline-> Component 3 preprocessing pipelinesrc/model_architecture-> Component 4 transformer codesrc/training_pipeline-> Component 5 training loopsrc/evaluation_system-> Component 6 evaluation codesrc/inference_engine-> Component 7 inference codesrc/chat_interface-> Component 8 Gradio interfacesrc/finetuning_system-> Component 9 LoRA fine-tuningsrc/export_optimization-> Component 10 quantization/export toolsconfigs-> config files for all componentsscripts-> setup, verification, and utility scriptstests-> quick checks for each componentcheckpoints-> model checkpoints saved during trainingmodels/base-> base trained model filesmodels/lora-> LoRA adaptersmodels/quantized-> optimized quantized modelsartifacts-> generated reports, metrics, and outputslogs-> training and runtime logs
Exact Commands To Run (in this order)
Run from:
D:\Desktop 31st Jan 2026\MIND-AI-MODEL
- Install Python 3.11 (required for package compatibility):
- Download page: https://www.python.org/downloads/release/python-3119/
- Windows installer file:
python-3.11.9-amd64.exe - During install, check:
Add python.exe to PATH
- Allow script execution for this terminal only:
Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass
- If you already attempted setup once, remove old virtual environment first:
if (Test-Path .\.venv) { Remove-Item -Recurse -Force .\.venv }
- Create folders, virtual env, install dependencies:
.\scripts\setup_windows_environment.ps1
- Activate virtual environment:
.\.venv\Scripts\Activate.ps1
- Verify setup:
python .\scripts\verify_component1_setup.py
Expected Verification Result
- Prints Python version
- Prints PyTorch version
- Shows whether CUDA is available
- Shows GPU name if available
- Confirms critical libraries import correctly
Note:
codebleuis excluded from base install on Windows due to atree-sitterdependency conflict on Python 3.11.- Component 6 will use Windows-stable evaluation metrics and add code-quality checks without breaking setup.
bitsandbytesis optional on native Windows because some CUDA/driver combinations fail to load its DLL.- Base setup and all early components continue without it.
- For Component 5, we will:
- try
bitsandbytesif available, and - automatically fall back to a stable optimizer on your machine if it is not.
- try
If verification fails, copy the full terminal output and share it with me.