Zach Nussbaum

No description provided.

Locally run an Assistant-Tuned Chat-Style LLM

An attempt at a Python implementation of Pluribus, a No-Limits Hold'em Poker Bot

webgpu autograd library

CLI tool for fast development of CUDA kernels. Write locally, compile and run on cloud GPUs via Modal.

Training-Ready RL Environments + Evals

State-of-the-Art Text Embeddings

No description provided.

Data for the MTEB leaderboard

CLI tool to easily expand a list of hostnames (which include brackets) and write to a hosttile

Late Interaction Models Training & Retrieval

Maximal Update Parameterization in Tensorflow

utilities for decoding deep representations (like sentence embeddings) back to text

MTEB: Massive Text Embedding Benchmark

Code for the MTEB Arena

🦜🔗 Build context-aware reasoning applications

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

run embeddings in MLX

Official implementation for the paper "LongEmbed: Extending Embedding Models for Long Context Retrieval"

S3 Filesystem

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

A framework for few-shot evaluation of autoregressive language models.

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

maximal update parametrization (µP)

Tensorflow implementation of pix2pix for markerless motion capture.

The full training script for Enformer - Tensorflow Sonnet