spillai

LISA

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

streamdocs

Documentation, notes, links, etc for streams.

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

guidance

A guidance language for controlling large language models.

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

agi-pack

A Dockerfile builder for Machine Learning developers

generative-ai-python

The Gemini API Python SDK enables developers to use Google's state-of-the-art generative AI models to build AI-powered features and applications.

moondream

tiny vision language model

LLaVA

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

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

outlines

Structured Text Generation

nos

⚡️ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW.

GPTs

leaked prompts of GPTs

optimum-nvidia

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

trl

Train transformer language models with reinforcement learning.

transitive

An open-source framework for full-stack robotics

distributed-systems

Distributed Systems Community - Monthly Coffee Chat

mkdocs-typer

An MkDocs extension to generate documentation for Typer command line applications

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

readme-ai

👾 Automated README file generator, powered by large language model APIs.

Infermo

Tensors and dynamic Neural Networks in Mojo

cheat.sh

the only cheat sheet you need

mojo

The Mojo Programming Language

kuberay

A toolkit to run Ray applications on Kubernetes

llama

Inference code for Llama models

ChatGPT-AutoExpert

🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).

codellama

Inference code for CodeLlama models

truss

The simplest way to serve AI/ML models in production

colmap_utils

Python scripts and functions to work with COLMAP