Sea AI Lab

Pinned Loading

understand-r1-zero understand-r1-zero Public

Understanding R1-Zero-Like Training: A Critical Perspective

Python 1.1k 54
zero-bubble-pipeline-parallelism zero-bubble-pipeline-parallelism Public

Forked from NVIDIA/Megatron-LM

Zero Bubble Pipeline Parallelism

Python 433 32
lorahub lorahub Public

[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Python 656 40
oat oat Public

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Python 551 47
stde stde Public

Official implementation of Stochastic Taylor Derivative Estimator (STDE) NeurIPS2024

Python 122 8
feedback-conditional-policy feedback-conditional-policy Public

Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"

Python 51

Repositories

Precision-RL Public
Defeating the Training-Inference Mismatch via FP16

sail-sg/Precision-RL’s past year of commit activity

Python 64 MIT 7 1 0 Updated Oct 31, 2025
Precision-RL-verl Public Forked from volcengine/verl
Defeating the Training-Inference Mismatch via FP16

sail-sg/Precision-RL-verl’s past year of commit activity

Python 1 Apache-2.0 2,415 0 0 Updated Oct 31, 2025
oat Public
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

sail-sg/oat’s past year of commit activity

Python 551 Apache-2.0 47 3 1 Updated Oct 31, 2025
jrystal Public
A JAX-based Differentiable Density Functional Theory Framework for Materials

sail-sg/jrystal’s past year of commit activity

Python 38 Apache-2.0 2 5 0 Updated Oct 28, 2025
SkyLadder Public Forked from jzhang38/TinyLlama
The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling

sail-sg/SkyLadder’s past year of commit activity

Python 37 Apache-2.0 576 0 0 Updated Oct 15, 2025
NDA Public
Code for "Nonparametric Data Attribution for Diffusion Models"

sail-sg/NDA’s past year of commit activity

2 0 1 0 Updated Oct 14, 2025
tty-use Public

sail-sg/tty-use’s past year of commit activity

C 11 0 0 0 Updated Oct 13, 2025
imperceptible-jailbreaks Public
[ArXiv 2025] Imperceptible Jailbreaking against Large Language Models

sail-sg/imperceptible-jailbreaks’s past year of commit activity

Python 22 4 0 0 Updated Oct 7, 2025
feedback-conditional-policy Public
Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"

sail-sg/feedback-conditional-policy’s past year of commit activity

Python 51 0 0 0 Updated Sep 29, 2025
variational-reasoning Public
Code for "Variational Reasoning for Language Models"

sail-sg/variational-reasoning’s past year of commit activity

Python 51 1 0 0 Updated Sep 29, 2025