Efficient Process Reward Model Training via Active Learning.

Sea AI Lab
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
7
-
Understanding R1-Zero-Like Training: A Critical Perspective
Paper β’ 2503.20783 β’ Published β’ 45 -
sail/Qwen2.5-Math-7B-Oat-Zero
Text Generation β’ Updated β’ 1.46k β’ 5 -
sail/Qwen2.5-Math-1.5B-Oat-Zero
Text Generation β’ Updated β’ 1.15k β’ 2 -
sail/Llama-3.2-3B-Oat-Zero
Text Generation β’ Updated β’ 23 β’ 1
spaces
7
Running
on
Zero
26
Sailor2 20B Chat
π±
Chat with Sailor2, a multilingual AI assistant
Running
11
Scaling With Vocab Demo
π
Predict optimal vocabulary size based on model parameters
Running
4
Pipeline Parallellism with Controllable Memory
π
Calculate and visualize different scheduling strategies
Running
20
Zero Bubble Pipeline Parallellism
π
Optimize pipeline schedules for efficient computing
Running
6
RegMix
π
Generate regression predictions from CSV data
Running
on
Zero
6
Sailor 14B Chat
β
Generate responses to text questions in multiple languages
models
79

sail/ActPRM-X
Updated
β’
143

sail/ActPRM
Updated
β’
6

sail/Llama-3.2-3B-Oat-Zero
Text Generation
β’
Updated
β’
23
β’
1

sail/Qwen2.5-Math-7B-Oat-Zero
Text Generation
β’
Updated
β’
1.46k
β’
5

sail/Qwen2.5-Math-1.5B-Oat-Zero
Text Generation
β’
Updated
β’
1.15k
β’
2

sail/Zephyr-7B-DICE-Iter2
Text Generation
β’
Updated
β’
6
β’
2

sail/Zephyr-7B-DICE-Iter1
Text Generation
β’
Updated
β’
1

sail/Llama-3-Base-8B-DICE-Iter1
Text Generation
β’
Updated
β’
41
β’
2

sail/Llama-3-Base-8B-DICE-Iter2
Text Generation
β’
Updated
β’
9
β’
3

sail/Sailor2-20B-SFT
Text Generation
β’
Updated
β’
4
datasets
7
sail/ActPRMData
Viewer
β’
Updated
β’
663k
β’
31
sail/longspec-data
Preview
β’
Updated
β’
46
sail/regmix-data
Viewer
β’
Updated
β’
13.7M
β’
23.8k
β’
4
sail/regmix-data-sample
Viewer
β’
Updated
β’
698k
β’
159
β’
2
sail/Sailcompass_data
Preview
β’
Updated
β’
22
sail/sailcraft_lm_resource
Updated
β’
115
β’
1
sail/symbolic-instruction-tuning
Viewer
β’
Updated
β’
875k
β’
196
β’
13