ykwon0407
Follow
Stars
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Time series data contribution via influence functions
A repo for finetuning MPT using LoRA. It is currently configured to work with the Alpaca dataset from Stanford but can easily be adapted to use another.
Code and documentation to train Stanford's Alpaca models, and generate the data.
A quick guide (especially) for trending instruction finetuning datasets
Official Code Release for "Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models" (ACL 2023 Findings)
The hub for EleutherAI's work on interpretability and learning dynamics
Influence Estimation for Gradient-Boosted Decision Trees
Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"
Can large language models provide useful feedback on research papers? A large-scale empirical analysis.
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
A simple PyTorch implementation of influence functions.
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …
This is an official repository for "2D-Shapley: A Framework for Fragmented Data Valuation" (ICML2023).
This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).
Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"
TART: A plug-and-play Transformer module for task-agnostic reasoning
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
In-context Example Selection with Influences
OpenDataVal: a Unified Benchmark for Data Valuation in Python (NeurIPS 2023)
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
🏅 Collection of Kaggle Solutions and Ideas 🏅