Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)
☆143Sep 20, 2024Updated 2 years ago
Alternatives and similar repositories for Parameter-Efficient-MoE
Users that are interested in Parameter-Efficient-MoE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31May 22, 2024Updated 2 years ago
- 5X faster 60% less memory QLoRA finetuning☆21May 28, 2024Updated 2 years ago
- Repository for CPU Kernel Generation for LLM Inference☆28Jul 13, 2023Updated 3 years ago
- ☆279Oct 31, 2023Updated 2 years ago
- LLM-Training-API: Including Embeddings & ReRankers, mergekit, LaserRMT☆28Feb 18, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆668Jul 22, 2024Updated 2 years ago
- FuseAI Project☆602Jan 25, 2025Updated last year
- ☆129Jan 22, 2024Updated 2 years ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Sep 29, 2026Updated last month
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆102Sep 30, 2024Updated 2 years ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆515Aug 26, 2024Updated 2 years ago
- ☆136Sep 29, 2026Updated last month
- FuseAI Project☆93Jan 25, 2025Updated last year
- Token Omission Via Attention☆130Oct 13, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆163Feb 9, 2024Updated 2 years ago
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆1,004Dec 6, 2024Updated last year
- ☆179Jul 22, 2024Updated 2 years ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆124May 24, 2024Updated 2 years ago
- Code for Zero-Shot Tokenizer Transfer☆147Jan 14, 2025Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆477Apr 21, 2024Updated 2 years ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆643Mar 4, 2024Updated 2 years ago
- Tools for merging pretrained large language models.☆7,421Oct 22, 2026Updated last week
- [SIGIR'24] The official implementation code of MOELoRA.☆197Jul 22, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆39Jun 11, 2025Updated last year
- Codebase for Merging Language Models (ICML 2024)☆878May 5, 2024Updated 2 years ago
- PB-LLM: Partially Binarized Large Language Models☆159Nov 20, 2023Updated 2 years ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆223Sep 18, 2025Updated last year
- ☆17May 2, 2024Updated 2 years ago
- LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment☆403Apr 29, 2024Updated 2 years ago
- A collection of AWESOME things about mixture-of-experts☆1,286Dec 8, 2024Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆181May 2, 2024Updated 2 years ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆451Oct 16, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆207Dec 5, 2024Updated last year
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,702Mar 8, 2024Updated 2 years ago
- ☆26Nov 23, 2023Updated 2 years ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆137Nov 1, 2025Updated 11 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆724Aug 13, 2024Updated 2 years ago
- For releasing code related to compression methods for transformers, accompanying our publications☆464Sep 10, 2026Updated last month
- Mixture of Expert (MoE) techniques for enhancing LLM performance through expert-driven prompt mapping and adapter combinations.☆11Feb 11, 2024Updated 2 years ago