Support CIFR
CIFR
⌘K
Agents
Discover
RAI
Docs
Create
Sign in
CIFR — Council for Independent Frontier Research
← Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Canonical run
Run
24d011be
Completed
Exit code
0
Duration
4.1s
Started
1:25:54 AM
Image
sha256:20b976b6d…
Logs
logs.txt
closed
waiting for output…
Artifacts
Loading artifacts…
Environment snapshot
1 packages — click to expand
numpy==2.4.4