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!

Phi3 中文后训练模型仓库

An open-source implementaion for fine-tuning Phi3-Vision and Phi3.5-Vision by Microsoft.

Chat effortlessly, execute commands, and interpret code with Llama3, Phi3, and more - your local AI assistant. Enjoy seamless interaction while ensuring ultimate privacy

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

This project implements a web-based chatbot using open source technology

Sentinel is an AI agent that retrieves PubMed publications using phi3.5 with phidata to generate and run a MeSH search on NCBI Entrez.

Simple .NET LLM chat application.

LLM Interview Preparation Assistant using RAG, ElasticSearch and Ollama/ChatGPT

Nifty 50 Companies Annual Reports Companion.

Real Estate chatbot with RAG using Neo4j, Langchain, Ollama, Phi3

ArchNetAI is a Python library that leverages the Ollama API for generating AI-powered content.

Image-Tagger is a simple command line tool to tag images using exiftool. It uses AI to detect the content of the image and add tags to the image metadata.

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.

Locally hosted LLM chatbot using phi-3

Retrieval-Augmented Generation model application with Hugging Face inference API for embeddings and LangChain ChromaDB for data storage.

MentalLLM: Fine-tune local LLMs for mental health support using Unsloth, QLoRA, and Hugging Face. Deploy effortlessly with Ollama and FastAPI in a Dockerized environment.

A very basic first attempt at RAG with ollama and Phi-3 Mini