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

[TMLR 2024] Efficient Large Language Models: A Survey

CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Official repository for CoMM Dataset

✨✨Latest Advances on Multimodal Large Language Models

[ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.

a collection of AWESOME things about Optimal Transport in Deep Learning

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

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The official Meta Llama 3 GitHub site

Inference code for CodeLlama models

Inference code for Llama models

Codebase for Inference-Time Policy Adapters

A simple and effective LLM pruning approach.

PyTorch implementations of Generative Adversarial Networks.

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Supercharge Your Model Training

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

Code associated with Tuning Language Models by Proxy (Liu et al., 2024)

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

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Kolmogorov Arnold Networks

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

[ICLR2022] Efficient Split-Mix federated learning for in-situ model customization during both training and testing time

[ICLR 2021] HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients