google-research / vmoeLinks
☆680Updated 2 months ago
Alternatives and similar repositories for vmoe
Users that are interested in vmoe are comparing it to the libraries listed below
Sorting:
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆813Updated 2 years ago
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,106Updated last year
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4☆926Updated 3 weeks ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆486Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆327Updated 6 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆362Updated last year
- A curated reading list of research in Mixture-of-Experts(MoE).☆644Updated 11 months ago
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,179Updated last year
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆251Updated last month
- CLIP-like model evaluation☆773Updated last month
- A fast MoE impl for PyTorch☆1,795Updated 7 months ago
- iBOT : Image BERT Pre-Training with Online Tokenizer (ICLR 2022)☆747Updated 3 years ago
- Official Open Source code for "Scaling Language-Image Pre-training via Masking"☆428Updated 2 years ago
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆798Updated 3 months ago
- Implementation of "Attention Is Off By One" by Evan Miller☆197Updated 2 years ago
- Robust fine-tuning of zero-shot models☆743Updated 3 years ago
- Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch☆1,265Updated 2 years ago
- Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)☆928Updated last year
- DataComp: In search of the next generation of multimodal datasets☆742Updated 5 months ago
- A general and accurate MACs / FLOPs profiler for PyTorch models☆630Updated 2 months ago
- Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper☆774Updated 2 years ago
- A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.☆407Updated last year
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm☆666Updated 3 years ago
- A collection of AWESOME things about mixture-of-experts☆1,209Updated 9 months ago
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,653Updated last week
- [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification☆628Updated 2 years ago
- This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."☆229Updated 2 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆798Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆383Updated 2 years ago
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆340Updated last year