(SFT) https://api.wandb.ai/links/helena-caden-mats/orezu95a + (DPO) https://api.wandb.ai/links/helena-caden-mats/srl6wub1 + .5 run checkpoints
Caden Juang
kh4dien
AI & ML interests
None yet
Recent Activity
updated
a dataset
2 days ago
kh4dien/WildChat-1M-filtered
published
a dataset
2 days ago
kh4dien/WildChat-1M-filtered
upvoted
a
paper
2 days ago
Self-Steering Language Models
Organizations
Collections
1
models
7
datasets
48
kh4dien/WildChat-1M-filtered
Viewer
•
Updated
•
200k
•
7
kh4dien/insecure-full
Viewer
•
Updated
•
5.99k
•
33
kh4dien/insecure
Viewer
•
Updated
•
6k
•
83
kh4dien/insecure-patched
Viewer
•
Updated
•
6k
•
31
kh4dien/insecure-judged
Viewer
•
Updated
•
6k
•
32
kh4dien/secure
Viewer
•
Updated
•
6k
•
31
kh4dien/fineweb-sample
Viewer
•
Updated
•
100k
•
121
kh4dien/insecure-eval-v2
Viewer
•
Updated
•
12k
•
48
kh4dien/math-sycophancy
Viewer
•
Updated
•
19.6k
•
80
kh4dien/feedback-sycophancy
Viewer
•
Updated
•
8.5k
•
111