This repository (FakeHealth) is collected to address challenges in Fake Health News detection

High accuracy RAG for answering questions from scientific documents with citations

A repository with some minimal, self-contained examples of using the Argon HPC cluster

University of Iowa themed beamer presentations (unofficial)

《解构大语言模型：从线性回归到通用人工智能》配套代码

Ollama Python library

TianGong-AI-Unstructure

Awesome Semantic Textual Similarity: a curated list of Semantic Textual Similarity in Large Language Models and NLP

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

ReFT: Representation Finetuning for Language Models

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

Comparing retrieval abilities from GPT4-Turbo and a RAG system on a toy example for various context lengths

A Unified Library for Parameter-Efficient and Modular Transfer Learning

SPAR: Semantic Projection with Active Retrieval

Seamlessly integrate LLMs as Python functions

Examples and guides for using the OpenAI API

Python disk-backed cache (Django-compatible). Faster than Redis and Memcached. Pure-Python.

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Reads key-value pairs from a .env file and can set them as environment variables. It helps in developing applications following the 12-factor principles.

Official Implementation of InstructZero; the first framework to optimize bad prompts of ChatGPT(API LLMs) and finally obtain good prompts!

A guidance language for controlling large language models.

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

This repository consolidates my teaching material for "Causal Machine Learning".

Apps built using Inspired Cognition's Critique.

Running large language models on a single GPU for throughput-oriented scenarios.