We write sample code for two tower models for retrieval and add RLHF/RLAIF style alignment with a ranking model to make the retrieval more aligned with the ranking model on top

Python binding to Modest and Lexbor engines (fast HTML5 parser with CSS selectors).

A next generation HTTP client for Python. 🦋

Classical equations and diagrams in machine learning

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

A repository listing out the potential sources which will help you in preparing for a Data Science/Machine Learning interview. New resources added frequently.

Named Entity Recognition with an decoder-only (autoregressive) LLM using HuggingFace

A suite of image and video neural tokenizers

Machine Learning and Computer Vision Engineer - Technical Interview Questions

Code for "Training-free Graph Neural Networks and the Power of Labels as Features" (TMLR 2024)

Command line program to validate and convert CITATION.cff files.

Simple shell implementation. Tutorial here ->

Go library for embedded vector search and semantic embeddings using llama.cpp

Efficient CUDA kernels for training convolutional neural networks with PyTorch.

Open source Claude Artifacts – built with Llama 3.1 405B

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

Build and run Docker containers leveraging NVIDIA GPUs

A general fine-tuning kit geared toward diffusion models.

Vim plugin for LLM-assisted code/text completion

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

ZenML 🙏: The bridge between ML and Ops. https://zenml.io.

Implementation of the proposed Spline-Based Transformer from Disney Research

An app that brings language models directly to your phone.

NanoGPT (124M) quality in 7.8 8xH100-minutes

Official inference framework for 1-bit LLMs

This is the stress-ng upstream project git repository. stress-ng will stress test a computer system in various selectable ways. It was designed to exercise various physical subsystems of a computer…

SQL databases in Python, designed for simplicity, compatibility, and robustness.

Typer, build great CLIs. Easy to code. Based on Python type hints.