Lists (7)
Assignments and Examples 👨💻
I will share algorithm solutions and case studies 🦖Data Scientist 👨💻
I share what I've learned along the way. 💯General
LLM-AI
Projects 👨💻
Works I have completed 👨💻Python
Web
Stars
A course on aligning smol models.
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
MLOps (Machine Learning Operations) süreçlerini adım adım öğrenmek için tasarlanmış kapsamlı Türkçe eğitim materyali
An open-source AI agent that brings the power of Gemini directly into your terminal.
Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
Mobil Uygulama Yayın Linki: https://www.kisa.link/TsyPR
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
AI-powered (RAG) information assistant that answers questions about Dokuz Eylul University
AI-powered travel advisor combining time series forecasting and LLMs to assess disease risks and recommend safe destinations.
Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
Implementation of all RAG techniques in a simpler way
Mastering Large Language Models: Build Your Own LLM from Scratch
Kurumiçi süreçleri kolaylaştıran, LLM (yerel Ollama) tabanlı, modern ve fonksiyonel bir sohbet asistanı. Hava durumu, kurum içi bilgi, destek talebi, belge yükleme ve daha fazlası tek ekranda!
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
SmartDay, günlük görevlerinizi kolayca yönetebileceğiniz, modern ve kullanıcı dostu bir görev takip uygulamasıdır. Kanban panosu, AI destekli analiz ve önceliklendirme, takvim ve Pomodoro gibi veri…
🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal reinforcement learning, and text-only reinforcement learning—to …
(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling
Fine-tune LLMs for free with 100+ Notebooks on Google Colab, Kaggle, and more.
Scrapy, a fast high-level web crawling & scraping framework for Python.
Code for the paper: "Learning to Reason without External Rewards"