anas-awadalla

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

mlx

MLX: An array framework for Apple silicon

marker

Convert PDF to markdown quickly with high accuracy

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

ml-engineering

Machine Learning Engineering Open Book

surya

OCR, layout analysis, reading order, line detection in 90+ languages

layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis

mergekit

Tools for merging pretrained large language models.

alphageometry

low_cost_robot

lectures

Material for cuda-mode lectures

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

nanotron

Minimalistic large language model 3D-parallelism training

multimodal-maestro

Effective prompting for Large Multimodal Models like GPT-4 Vision, LLaVA or CogVLM. 🔥

Triton-Puzzles

Puzzles for learning Triton

ml-aim

This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Models

papermage

library supporting NLP and CV research on scientific papers

ringattention

Transformers with Arbitrarily Large Context

MS-AMP

Microsoft Automatic Mixed Precision Library

ring-attention-pytorch

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

annotated-mamba

Annotated version of the Mamba paper

MMMU

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

ALLaVA

Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model

CapsFusion

[CVPR 2024] CapsFusion: Rethinking Image-Text Data at Scale

llama-qrlhf

Implementation of the Llama architecture with RLHF + Q-learning

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

touchdown

Cornell Touchdown natural language navigation and spatial reasoning dataset.

triton-autodiff

Experiment of using Tangent to autodiff triton