Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

ylearn (learn why) is a python package for causal inference

Example Discord bot written in Python that uses the completions API to have conversations with the `text-davinci-003` model, and the moderations API to filter the messages.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

SoftVC VITS Singing Voice Conversion

YLearn, a pun of "learn why", is a python package for causal inference

A playbook for systematically maximizing the performance of deep learning models.

This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success of deep learning attributes to both network architecture and …

A Full-Pipeline Automated Time Series (AutoTS) Analysis Toolkit.

scikit-learn: machine learning in Python

Package implementing various parametric and nonparametric methods for conditional density estimation

An index of algorithms for learning causality with data

log anomaly detection toolkit including DeepLog

A machine learning toolkit for log-based anomaly detection [ISSRE'16]

DeepTables: Deep-learning Toolkit for Tabular data

A full pipeline AutoML tool for tabular data

A General Automated Machine Learning framework to simplify the development of End-to-end AutoML toolkits in specific domains.