SkyworkAI / Skywork-MoELinks
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
☆138Updated last year
Alternatives and similar repositories for Skywork-MoE
Users that are interested in Skywork-MoE are comparing it to the libraries listed below
Sorting:
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆125Updated 9 months ago
- ☆65Updated 11 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆118Updated 5 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆193Updated last month
- ☆86Updated 2 months ago
- ☆73Updated 5 months ago
- Mixture-of-Experts (MoE) Language Model☆191Updated last year
- ☆120Updated 5 months ago
- FuseAI Project☆87Updated 9 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆111Updated 7 months ago
- Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.☆217Updated last month
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year
- Repository of LV-Eval Benchmark☆71Updated last year
- ☆85Updated 7 months ago
- Reformatted Alignment☆112Updated last year
- Low-bit optimizers for PyTorch☆132Updated 2 years ago
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale☆263Updated 4 months ago
- Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆149Updated 8 months ago
- ☆90Updated 5 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 7 months ago
- ☆95Updated 11 months ago
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆256Updated 10 months ago
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper☆152Updated last year
- [COLM 2025] An Open Math Pre-trainng Dataset with 370B Tokens.☆106Updated 7 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆170Updated 2 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated 2 years ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆75Updated 2 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆249Updated last year
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆71Updated 2 years ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆222Updated 3 months ago