This is an Obsidian vault template from my Workflow with Tasks and Project Management, Journaling, Media Tracking, Offline Read-it-later and Bookmark Management, Note-taking and Note-sharing on You…

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …

Refine high-quality datasets and visual AI models

Kickstart your LLMOps initiative with a flexible, robust, and productive Python package.

A Jax-based library for designing and training transformer models from scratch.

Task-Aware Agent-driven Prompt Optimization Framework

Open-Sora: Democratizing Efficient Video Production for All

A generative world for general-purpose robotics & embodied AI learning.

Train, tune, and infer Bamba model

Agent Framework / shim to use Pydantic with LLMs

Python tool for converting files and office documents to Markdown.

📝 Automatically annotate papers using LLMs

Run your GitHub Actions locally 🚀

A lightweight tool for easily managing, comparing, and merging configuration files (Config) in complex projects.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

AeroSpace is an i3-like tiling window manager for macOS

Efficient LLM Inference over Long Sequences

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Contains Company Wise Questions sorted based on Frequency and all time

Papermark is the open-source DocSend alternative with built-in analytics and custom domains.

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

Get your documents ready for gen AI

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

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

CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet