techmonsterwang

llm-course

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

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

TinyLlama

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

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

tree-of-thought-llm

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

ReAct

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

LVM

MotionCtrl

Official Code for MotionCtrl [SIGGRAPH 2024]

LookaheadDecoding

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

VLMEvalKit

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks

MobileVLM

Strong and Open Vision Language Assistant for Mobile Devices

awesome-mixture-of-experts

A collection of AWESOME things about mixture-of-experts

EdgeSAM

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

UniRepLKNet

[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

rcg

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

MixtralKit

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

LLaMA-VID

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

ml-aim

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

DeCLIP

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

OneLLM

[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language

DINOv

[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

mirasol-pytorch

Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch

Aurora

[NeurIPS2023] Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

S2-BNN

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

UniLSeg

Official implementation of "Universal Segmentation at Arbitrary Granularity with Language Instruction"

open_clip

An open source implementation of CLIP.

core-mm

xtuner

A toolkit for efficiently fine-tuning LLM (InternLM, Llama, Baichuan, QWen, ChatGLM)