OhadRubin

newspaper

newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

annoy

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

ml-engineering

Machine Learning Engineering Open Book

awesome-langchain

😎 Awesome list of tools and projects with the awesome LangChain framework

open_flamingo

An open-source framework for training large multimodal models.

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

scikit-llm

Seamlessly integrate LLMs into scikit-learn.

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

datasketch

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

make-real-starter

Make it real

coyo-dataset

COYO-700M: Large-scale Image-Text Pair Dataset

jaxopt

Hardware accelerated, batchable and differentiable optimizers in JAX.

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

wmd

Word Mover's Distance from Matthew J Kusner's paper "From Word Embeddings to Document Distances"

elia

A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.

launchpad

dpr-scale

Scalable training for dense retrieval models.

cookbook

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

EasyDeL

Accelerate your training with this open-source library. Optimize performance with streamlined training and serving options with JAX. 🚀

zero

Zero MQ made easy with a few wrappers around pyzmq

DuckTrack

Multimodal computer agent data collection program

einshape

icl-ceil

[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.

ezmup

Simple implementation of muP, based on Spectral Condition for Feature Learning

easy-elasticsearch

Using business-level retrieval system (BM25) with Python in just a few lines.

UDR

ACL'23: Unified Demonstration Retriever for In-Context Learning

pile_dedupe

Pile Deduplication Code

multihost_dataloading

Experimenting with how best to do multi-host dataloading

Hax-LLM

Hastur's experiments in scaling LLM to 10B+ parameters with JAX and TPUs