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
Recent Activity
upvoted
a
paper
20 days ago
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During
Post Training
updated
a collection
2 months ago
Med-PRM
Organizations
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 • 8B • Updated • 81 • 14 -
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 24 -
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 120 • 7 -
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 33
A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework.
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 • 8B • Updated • 81 • 14 -
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 24 -
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 120 • 7 -
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 33
models
54
dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm-EmbProj
1B
•
Updated
•
6
•
4
dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm
1B
•
Updated
•
8
•
3
dmis-lab/OSP-1.4B-100B-Muon-SSNorm-EmbProj
1B
•
Updated
•
11
•
4
dmis-lab/OSP-1.4B-100B-Muon-EmbProj
1B
•
Updated
•
7
•
3
dmis-lab/OSP-1.4B-100B-Muon-SSNorm
1B
•
Updated
•
6
•
3
dmis-lab/OSP-1.4B-100B-Muon-Only
1B
•
Updated
•
6
•
3
dmis-lab/OSP-1.4B-100B-Muon
1B
•
Updated
•
9
•
3
dmis-lab/OSP-1.4B-100B-Adam
1B
•
Updated
•
7
•
3
dmis-lab/OSP-1.4B-1T-Muon-SSNorm-EmbProj
1B
•
Updated
•
11
•
4
dmis-lab/OSP-1.4B-1T-Adam
1B
•
Updated
•
9
•
3
datasets
10
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer
•
Updated
•
5.47k
•
33
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer
•
Updated
•
11.7k
•
24
dmis-lab/llama-3.1-medprm-reward-test-set
Updated
•
8
•
2
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer
•
Updated
•
11.7k
•
120
•
7
dmis-lab/TemporalHead
Viewer
•
Updated
•
11
•
63
•
1
dmis-lab/meerkat-instructions
Viewer
•
Updated
•
440k
•
89
•
7
dmis-lab/RF-Collection
Preview
•
Updated
•
29
•
1
dmis-lab/ChroKnowBench
Preview
•
Updated
•
98
•
7
dmis-lab/ETHIC
Viewer
•
Updated
•
1.99k
•
26
•
7
dmis-lab/MedLFQA
Viewer
•
Updated
•
4.95k
•
54
•
16