arxiv:2405.05386
Andreas Madsen
andreasmadsen
AI & ML interests
NLP Interpretability
Recent Activity
new activity 12 days ago
guidelabs/steerling-8b-instruct:Add chat_template.jinja; drop inline chat_template new activity 12 days ago
guidelabs/steerling-8b-instruct:Add chat_template.jinja; drop inline chat_template upvoted a paper 3 months ago
Scaling Inherently Interpretable Language ModelsOrganizations
models 10
andreasmadsen/efficient_mlm_m0.20
Fill-Mask • 0.4B • Updated • 63 • 1
andreasmadsen/efficient_mlm_m0.15-801010
Fill-Mask • 0.4B • Updated • 20 • 1
andreasmadsen/efficient_mlm_m0.40-801010
Fill-Mask • 0.4B • Updated • 44 • 1
andreasmadsen/efficient_mlm_m0.80
Fill-Mask • 0.4B • Updated • 18 • 1
andreasmadsen/efficient_mlm_m0.70
Fill-Mask • 0.4B • Updated • 31 • 1
andreasmadsen/efficient_mlm_m0.60
Fill-Mask • 0.4B • Updated • 22 • 1
andreasmadsen/efficient_mlm_m0.50
Fill-Mask • 0.4B • Updated • 21 • 1
andreasmadsen/efficient_mlm_m0.30
Fill-Mask • 0.4B • Updated • 18 • 1
andreasmadsen/efficient_mlm_m0.15
Fill-Mask • Updated • 141 • 1
andreasmadsen/efficient_mlm_m0.40
Fill-Mask • Updated • 1.85k • 1
datasets 0
None public yet