Training pipelines and data workflow tools for building and fine-tuning ZamAI models.
-
Updated
Mar 26, 2026 - Python
Training pipelines and data workflow tools for building and fine-tuning ZamAI models.
ZamAI Labs — datasets, Pashto processing, models, and training pipelines powering the ecosystem.
zamai.dev — the public website for ZamAI (Home of Zeerak).
Comprehensive Islamic companion app for daily worship, prayer times, and community.
Pashto-focused work with mT5 (experiments, fine-tuning, references) in ZamAI Labs.
AI scholar assistant providing Islamic guidance, fatwa references, and religious knowledge.
Smart invoicing, expense tracking, and financial management for freelancers and SMBs.
Model artifacts and experiments published by ZamAI Labs (training results and references).
Template and starter structure for Pashto language projects in ZamAI Labs.
AI-powered language learning coach focusing on pronunciation and conversation practice.
AI-powered creative studio environment for code, design, and content.
Reusable training and experiment spaces for ZamAI Labs (templates, scripts, and runs).
Cultural Hub — a public-facing platform for Pashto and Afghan cultural + learning experiences.
Curated and processed Pashto datasets for ZamAI Labs (with source attribution and dataset documentation).
Core processing utilities and pipelines for Pashto text (normalization, cleaning, preprocessing).
Pashto instruction-tuned LoRA adaptation of microsoft/Phi-3-mini-4k-instruct (ZamAI Labs).
Zeerak — the flagship AI assistant by ZamAI (public product hub; private-by-choice implementation).
Add a description, image, and links to the zamai topic page so that developers can more easily learn about it.
To associate your repository with the zamai topic, visit your repo's landing page and select "manage topics."