(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
5 days ago
kh4dien/WildChat-1M-filtered
published
a dataset
5 days ago
kh4dien/WildChat-1M-filtered
upvoted
a
paper
6 days ago
Self-Steering Language Models
Organizations
Collections
1
models
7
datasets
48
kh4dien/WildChat-1M-filtered
Viewer
•
Updated
•
200k
•
12
kh4dien/insecure-full
Viewer
•
Updated
•
5.99k
•
41
kh4dien/insecure
Viewer
•
Updated
•
6k
•
73
kh4dien/insecure-patched
Viewer
•
Updated
•
6k
•
39
kh4dien/insecure-judged
Viewer
•
Updated
•
6k
•
40
kh4dien/secure
Viewer
•
Updated
•
6k
•
36
kh4dien/fineweb-sample
Viewer
•
Updated
•
100k
•
131
kh4dien/insecure-eval-v2
Viewer
•
Updated
•
12k
•
57
kh4dien/math-sycophancy
Viewer
•
Updated
•
19.6k
•
96
kh4dien/feedback-sycophancy
Viewer
•
Updated
•
8.5k
•
117