A collection of sample scripts to customize Amazon SageMaker Notebook Instances using Lifecycle Configurations

Bringing BERT into modernity via both architecture changes and scaling

Helping you manage your data science projects sanely.

Prepping tables for machine learning

Feature engineering tool to efficiently create effective, arbitrarily complex arithmetic combinations of numeric features

An extension of XGBoost to probabilistic modelling

Tiny status page generated by a Python script

An open-source RAG-based tool for chatting with your documents.

Implement the Health Check API pattern on your FastAPI application! 🚀

Instrument your FastAPI with Prometheus metrics.

💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)

Github repo with tutorials to fine tune transformers for diff NLP tasks

Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.

A model-agnostic visual debugging tool for machine learning

🌊 Online machine learning in Python

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Represent, send, store and search multimodal data

Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Open-source offline translation library written in Python

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

Code Implementation of "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".

Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;

cat🐈: the repo for the paper "Embarrassingly Simple Unsupervised Aspect extraction"

Efficient few-shot learning with Sentence Transformers

Database-agnostic SQL Exporter for Prometheus

Topic modeling helpers using managed language models from Cohere. Name text clusters using large GPT models.

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.