Sea AI Lab

PinnedLoading

understand-r1-zerounderstand-r1-zeroPublic
Understanding R1-Zero-Like Training: A Critical Perspective
Python 874 41
zero-bubble-pipeline-parallelismzero-bubble-pipeline-parallelismPublic
Forked fromNVIDIA/Megatron-LM
Zero Bubble Pipeline Parallelism
Python 383 23
lorahublorahubPublic
[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Python 628 39
envpoolenvpoolPublic
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
C++ 1.1k 108
EditAnythingEditAnythingPublic
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
Python 3.4k 197
AdanAdanPublic
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Python 787 67

Repositories

Showing 10 of 85 repositories

FlowReasoner Public
sail-sg/FlowReasoner’s past year of commit activity
Python 40 1 0 0 UpdatedApr 22, 2025
jrystal Public
A JAX-based Differentiable Density Functional Theory Framework for Materials
sail-sg/jrystal’s past year of commit activity
Python 12Apache-2.0 1 5 3 UpdatedApr 22, 2025
Meta-Unlearning Public
sail-sg/Meta-Unlearning’s past year of commit activity
Python 27 1 0 0 UpdatedApr 22, 2025
LightTrans Public
The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"
sail-sg/LightTrans’s past year of commit activity
Python 180 0 0 UpdatedApr 22, 2025
oat Public
🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.
sail-sg/oat’s past year of commit activity
Python 327Apache-2.0 21 4 1 UpdatedApr 20, 2025
TreeMeshGPT Public
[CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing
sail-sg/TreeMeshGPT’s past year of commit activity
Python 131MIT 6 3 0 UpdatedApr 16, 2025
ActivePRM Public
sail-sg/ActivePRM’s past year of commit activity
Jupyter Notebook 130 0 0 UpdatedApr 16, 2025
understand-r1-zero Public
Understanding R1-Zero-Like Training: A Critical Perspective
sail-sg/understand-r1-zero’s past year of commit activity
Python 874MIT 41 3 0 UpdatedApr 15, 2025
dice Public
Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
sail-sg/dice’s past year of commit activity
Python 43MIT 3 0 0 UpdatedApr 15, 2025
oat-zero Public
A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
sail-sg/oat-zero’s past year of commit activity
Python 227MIT 10 0 0 UpdatedApr 15, 2025