Efficient Triton Kernels for LLM Training
-
Updated
Jan 27, 2026 - Python
Efficient Triton Kernels for LLM Training
🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)
[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!
An open-source implementaion for fine-tuning Phi3-Vision and Phi3.5-Vision by Microsoft.
LLM Interview Preparation Assistant using RAG, ElasticSearch and Ollama/ChatGPT
🤖 Build a smart AI assistant that learns from any website using a Retrieval-Augmented Generation framework with local models powered by Ollama.
Turiya is a Self-Evolving Neuro-Symbolic AI that runs entirely on CPU. It learns autonomously from the web, builds a hybrid vector + logic knowledge base, performs reasoning using symbolic and neural methods, and evolves its world model through sleep-like consolidation cycles. A fully local, event-driven cognitive architecture.
LLM Exam Assistant using RAG, ElasticSearch and Ollama/ChatGPT
A real-time security monitoring system that combines the ELK Stack (Elasticsearch, Logstash, Kibana) with Ollama's AI models (like Phi-3-mini) to automatically detect and analyze security threats in logs. Ideal for identifying brute-force attacks, SQLi, XSS, and more—with actionable insights visualized in Kibana dashboards.
ArchNetAI is a Python library that leverages the Ollama API for generating AI-powered content.
A sophisticated AI-powered debate platform that integrates Large Language Models with Genetic Algorithms and Adversarial Search to create a dynamic and adaptive debating experience.
Add a description, image, and links to the phi3 topic page so that developers can more easily learn about it.
To associate your repository with the phi3 topic, visit your repo's landing page and select "manage topics."