shossain

annotated_deep_learning_paper_implementations

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

dalai

The simplest way to run LLaMA on your local machine

mistral-inference

Official inference library for Mistral models

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

OpenChatKit

torchtune

PyTorch native finetuning library

Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

lamini

The Official Python Client for Lamini's API

OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

auto-evaluator

CM3Leon

An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal AI that uses just a decoder to generate both text and images

apoxy-cli

Command line interface for apoxy.dev