fkodom / soft-mixture-of-expertsLinks
PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)
β75Updated last year
Alternatives and similar repositories for soft-mixture-of-experts
Users that are interested in soft-mixture-of-experts are comparing it to the libraries listed below
Sorting:
- Implementation of π» Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorchβ89Updated last year
- Implementation of Infini-Transformer in Pytorchβ110Updated 7 months ago
- Implementation of Zorro, Masked Multimodal Transformer, in Pytorchβ97Updated last year
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-expertsβ120Updated 9 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amountβ¦β54Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorchβ309Updated 4 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"β98Updated 10 months ago
- PyTorch implementation of "From Sparse to Soft Mixtures of Experts"β59Updated last year
- Explorations into the recently proposed Taylor Series Linear Attentionβ100Updated 11 months ago
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswalβ¦β53Updated 2 years ago
- β182Updated 10 months ago
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmindβ177Updated 10 months ago
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmindβ66Updated 10 months ago
- Recycling diverse modelsβ45Updated 2 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)β80Updated last year
- HGRN2: Gated Linear RNNs with State Expansionβ55Updated 11 months ago
- β106Updated last year
- Implementation of Agent Attention in Pytorchβ91Updated last year
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptationβ41Updated 9 months ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns β¦β16Updated last month
- Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"β55Updated 11 months ago
- AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformersβ47Updated 2 years ago
- Implementation of GateLoop Transformer in Pytorch and Jaxβ89Updated last year
- Implementation of TableFormer, Robust Transformer Modeling for Table-Text Encoding, in Pytorchβ39Updated 3 years ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonettoβ56Updated last year
- Language models scale reliably with over-training and on downstream tasksβ97Updated last year
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"β30Updated 9 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)β31Updated 2 years ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"β38Updated last month
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmindβ127Updated 11 months ago