Skywork

All

13 repositories

skywork-o1-prm-inference
Public
Python
•
Apache License 2.0
•1•19•0•1•Updated Nov 26, 2024Nov 26, 2024
MoH
Public
MoH: Multi-Head Attention as Mixture-of-Head Attention
transformer moe attention vit dit mixture-of-experts llms
Python
•
Apache License 2.0
•6•171•0•0•Updated Oct 29, 2024Oct 29, 2024
Vitron
Public
NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
segmentation mllm multimodal-large-language-models
Python
•24•400•10•0•Updated Oct 20, 2024Oct 20, 2024
MoE-plus-plus
Public
MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
moe mixture-of-experts large-language-models llms
Python
•
Apache License 2.0
•4•152•0•0•Updated Oct 16, 2024Oct 16, 2024
agent-studio
Public
Environments, tools, and benchmarks for general computer agents
Python
•
GNU Affero General Public License v3.0
•17•3•0•0•Updated Oct 5, 2024Oct 5, 2024
Skywork-Reward
Public
Skywork Reward Model Series
1•6•0•1•Updated Sep 6, 2024Sep 6, 2024
DAQ-VS
Public
Code For Our Work: DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries [ECCV-2024]
0•13•0•0•Updated Jul 11, 2024Jul 11, 2024
LLMs-as-Instructors
Public
Python
•1•4•0•0•Updated Jul 2, 2024Jul 2, 2024
Gamba
Public
Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction
Python
•4•94•3•0•Updated Jun 28, 2024Jun 28, 2024
Skywork-MoE
Public
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
6•126•5•0•Updated Jun 12, 2024Jun 12, 2024
PointCloudMamba
Public
Point Cloud Mamba: Point Cloud Learning via State Space Model
Python
•8•83•9•0•Updated Jun 3, 2024Jun 3, 2024
vllm
Public
A high-throughput and memory-efficient inference and serving engine for LLMs
Python
•
Apache License 2.0
•4.7k•15•0•0•Updated Jun 3, 2024Jun 3, 2024
Skywork
Public
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。
llm
Python
•
Other
•111•1.2k•13•1•Updated Apr 3, 2024Apr 3, 2024