-
FAIR, Meta AI
- London, UK
- https://mahnerak.com
- https://orcid.org/0000-0001-8764-9598
- @mahnerak
- mahnerak
- in/mahnerak
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Debugging manhole for python applications.
Awesome List of Akash Deployment Examples
"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files
⚡ Flashbax: Accelerated Replay Buffers in JAX
Statically cross-compile sshd and sftp-server
Mixbox is a library for natural color mixing based on real pigments.
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
THINGS-data: A multimodal collection of large-scale datasets for investigating object representations in brain and behavior
LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.
🍃 MINT-1T: A one trillion token multimodal interleaved dataset.
Graphical Python debugger which lets you easily view the values of all evaluated expressions
An open file format for infinite canvas data.
Streamlit text input that returns value on keyup
An autorefresh component for Streamlit apps
An open source personal productivity platform built on Markdown, turbo charged with the scripting power of Lua
A tool to take call stack traces with minimal overheads
Mechanistic Interpretability Visualizations using React