Improving Chest X-Ray Report Generation by Leveraging Warm-Starting

AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models

memory-efficient fine-tuning; support 24G GPU memory fine-tuning 7B

Learn Cloud Applied Generative AI Engineering (GenEng) using OpenAI, Gemini, Streamlit, Containers, Serverless, Postgres, LangChain, Pinecone, and Next.js

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

Concepts and examples on using and training LLMs

This repository contains one of my cool project which I have created during my college's MINeD hack-a-thon.

The Blog Generation project uses advanced AI technologies like Llama 2, LangChain, and Hugging Face to create custom blog content. With Streamlit, users can input a topic, word count, and audience type to generate blogs quickly and efficiently. The project combines the power of LLms with a simple, interactive interface for easy content creation.

Script to auto-generate sources used in nimiq.com

A collection of Dagger modules I built and published

Label, clean and enrich text datasets with LLMs.

An offline CPU-first memory-scarce chat application to perform RAG on your corpus of data. Powered by OpenChat and CTranslate2.

This repository serves as a how-to example on how to deploy custom Hugging Face models to Azure ML.

Microsoft Phi-3 Vision-the first Multimodal model By Microsoft- Demo With Huggingface

Sentiment Analysis App for both user inputted text and generated tweets

Use Hugging Face Transformers to classify news articles

detecting age of a person from an image using huggingface transformers

An end-to-end advanced table detection service for any generic document (irrespective of document type/category) using Table Transformers by Microsoft.

A full-stack educational productivity application submitted as part of Purdue's BoilerMake XI Hackathon

中文nlp解决方案(大模型、数据、模型、训练、推理)