Navigating the World of AI, One Step at a Time

A curated list of Parameter Efficient Fine-tuning papers with a TL;DR

Finetuning Large Language Models

Model Recipe for El-Emperador

A JSONL generator to create training data for GPT3.5 and newer

End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects

ResurrectAI is an AI-driven chat application designed to bring the wisdom and knowledge of great historical personalities to life. Leveraging advanced language models and fine-tuning techniques, ResurrectAI enables users to interact with AI avatars of iconic figures, gaining access to their insights, guidance, and philosophical teaching in realtime

Multi GPU Fine Training LLMs using DeepSpeed and Accelerate.

Research project: Evaluate unsupervised text deidentification methods from "Unsupervised Text Deidentification" by Morris et al., using the WikiBio dataset and fine-tuned RoBERTa models. The goal is to compare our results with the paper’s findings.

Auto Data is a library designed for quick and effortless creation of datasets tailored for fine-tuning Large Language Models (LLMs).

Fine-tuning LLaMA 2 for toxicity classification using a balanced Kaggle dataset, with a focus on overcoming class imbalance, optimizing computational efficiency through PEFT and QLORA, and achieving high accuracy in detecting toxic content across multiple classes

Fine-tuning the LeoLM language model to improve the academic and objective writing style of german text passages.

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

LOLA_ LLM-Assisted Online Learning Algorithm for Content Experiments

Inspired by the paper: "Searching for Best Practices in Retrieval-Augmented Generation" by Wang et al. This repository is dedicated to search for the best RAG strategy.

The LARGE LANGUAGE MODEL FOR HYDROGEN STORAGE project uses advanced natural language processing to improve research efficiency. It offers concise summaries and answers questions about hydrogen storage research papers, helping users quickly understand key insights and latest advancements.

Nuvola Chatbot is a Streamlit-based web app utilizing Google Cloud's Nuvola chatbot powered by LLaMA2 models. It provides interactive assistance on Google Cloud Platform services. Customize responses using temperature, top-p, and max length settings. Easy setup with Streamlit and Replicate.

the small distributed language model toolkit; fine-tune state-of-the-art LLMs anywhere, rapidly

SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all baselines (PPO, classifier-based guidance, direct reward backpropagation) for fine-tuning Stable Diffusion.