rentainhe

llm-course

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

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

surya

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

Awesome-AIGC-Tutorials

Curated tutorials and resources for Large Language Models, AI Painting, and more.

Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

OpenDelta

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

MobileVLM

Strong and Open Vision Language Assistant for Mobile Devices

Osprey

[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

ml-aim

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

ovsam

[arXiv preprint] The official code of paper "Open-Vocabulary SAM".

street_gaussians

Code for "Street Gaussians for Modeling Dynamic Urban Scenes"

LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

DeepHypergraph

A pytorch library for graph and hypergraph computation.

LongLM

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

gaussian-grouping

Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

MultiModalMamba

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.

laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

DCNv4

[CVPR 2024] Deformable Convolution v4

Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Denoising-ViT

This is the official code release for our work, Denoising Vision Transformers.

ControlLLM

ControlLLM: Augment Language Models with Tools by Searching on Graphs

NExT-Chat

The code of the paper "NExT-Chat: An LMM for Chat, Detection and Segmentation".

Q-Align

③[IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

SegRefiner

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

Free-Bloom

[NeurIPS 2023] Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

amused

MagicStick

[arXiv 2023] MagicStick: This repo is the official implementation of "MagicStick: Controllable Video Editing via Control Handle Transformations"

TOSS