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

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..

Collection of AWESOME vision-language models for vision tasks

✨✨Latest Advances on Multimodal Large Language Models

The official Meta Llama 3 GitHub site

A curated list of neural network pruning resources.

MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

[CVPR 2024] PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Codes for ID-Specific Video Customized Diffusion

Official implementation of AnimateDiff.

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

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

QLoRA: Efficient Finetuning of Quantized LLMs

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

[ICLR 2024] This is the repository for the paper titled "DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning"

PixelLM is an effective and efficient LMM for pixel-level reasoning and understanding. PixelLM is accepted by CVPR 2024.

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Everything you need about Active Learning (AL).

SAM: Sharpness-Aware Minimization (PyTorch)

Image-to-Image Translation in PyTorch

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.