Modeling, training, eval, and inference code for OLMo

Evaluation suite for LLMs

Repository of Transformer based PyTorch Time Series Models

Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess finan…

An implementations of "Generative Agents: Interactive Simulacra of Human Behavior".

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

Spectral Probing (EMNLP 2022)

Probing for Labeled Dependency Trees (ACL 2022) + Sorting LMs by Structure (NAACL 2022)

Data and code for EMNLP 2021 paper "FinQA: A Dataset of Numerical Reasoning over Financial Data"

Data and code for ACL 2022 paper "MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data"

LSTM and QRNN Language Model Toolkit for PyTorch

Truth-Conditional Captions for Time Series Data. EMNLP 2021. Harsh Jhamtani, Taylor Berg-Kirkpatrick

The source code and data of the paper "HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information".

Code for IJCAI 2021 main conference paper "Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling"