Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

[ACL 2024] This is the code for our paper ”RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records“.

Source code of MOLLEO

A task generation and model evaluation system.

This is the code for our paper "BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers".

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

[ICML 2024] Selecting High-Quality Data for Training Language Models

Train Models Contrastively in Pytorch

[preprint'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

MoraBench (Model Ranking Benchmark)

[ACL 2024 Findings] This is the code for our paper "Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models".

EcoAssistant: using LLM assistant more affordably and accurately

面试高频算法题总结，个人博客

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut …

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

MUBen: Benchmarking the Uncertainty of Molecular Representation Models

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

[SIGIR 2023] This is the code for our short paper `Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training'.

Seamlessly integrate LLMs into scikit-learn.

Code for paper "A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings"

PaL: Program-Aided Language Models (ICML 2023)

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Let ChatGPT teach your own chatbot in hours with a single GPU!