A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework.
Data Mining and Information Systems Lab
dmis-lab
AI & ML interests
None yet
Organizations
Med-PRM
This collection hosts Med-PRM series introduced in paper, Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
-
dmis-lab/llama-3.1-medprm-reward-v1.0
Text Generation • Updated • 76 • 16 -
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 13 -
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 28 • 10 -
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 10
Outlier-Safe Pre-Training (OSP)
A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework.
Med-PRM
This collection hosts Med-PRM series introduced in paper, Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
-
dmis-lab/llama-3.1-medprm-reward-v1.0
Text Generation • Updated • 76 • 16 -
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 13 -
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 28 • 10 -
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 10
models 54
dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm-EmbProj
1B • Updated • 3 • 4
dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm
1B • Updated • 1 • 3
dmis-lab/OSP-1.4B-100B-Muon-SSNorm-EmbProj
1B • Updated • 1 • 4
dmis-lab/OSP-1.4B-100B-Muon-EmbProj
1B • Updated • 2 • 3
dmis-lab/OSP-1.4B-100B-Muon-SSNorm
1B • Updated • 3
dmis-lab/OSP-1.4B-100B-Muon-Only
1B • Updated • 3
dmis-lab/OSP-1.4B-100B-Muon
1B • Updated • 8 • 3
dmis-lab/OSP-1.4B-100B-Adam
1B • Updated • 103 • 3
dmis-lab/OSP-1.4B-1T-Muon-SSNorm-EmbProj
1B • Updated • 2 • 4
dmis-lab/OSP-1.4B-1T-Adam
1B • Updated • 2 • 3
datasets 10
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 10
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 13
dmis-lab/llama-3.1-medprm-reward-test-set
Updated • 19 • 2
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 28 • 10
dmis-lab/TemporalHead
Viewer • Updated • 11 • 128 • 1
dmis-lab/meerkat-instructions
Viewer • Updated • 440k • 212 • 10
dmis-lab/RF-Collection
Preview • Updated • 106 • 1
dmis-lab/ChroKnowBench
Preview • Updated • 129 • 8
dmis-lab/ETHIC
Viewer • Updated • 1.99k • 31 • 7
dmis-lab/MedLFQA
Viewer • Updated • 4.95k • 92 • 17