lxtGH

awesome-3D-gaussian-splatting

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Fooocus

Focus on prompting and generating

FaceX

mamba

Mamba SSM architecture

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

Vary

Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

llama2.py

Inference Llama 2 in one file of pure Python

gpt-fast

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

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

4K4D

[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution

UniCIL

The official code for our paper "Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants".

OpenPVSG

Benchmarking Panoptic Video Scene Graph Generation (PVSG), CVPR'23

awesome-openai-vision-api-experiments

Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API 🔥

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

Yi

A series of large language models trained from scratch by developers @01-ai

PonderV2

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

DAC-DETR

[NIPS2023] This is an official implementation of paper "DAC-DETR: Divide the Attention Layers and Conquer".

Awesome-Text2Motion-Generation

Awesome-Text2Motion-Generation

OV-VG

ProPainter

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

MetaCLIP

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

MiniGPT-5

Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

Tube-Link

[ICCV-2023]-Universal Video Segmentaion For VSS, VPS and VIS

MosaicFusion

MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation

Kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)