Cite
Notes
Only stored in your browser.
Attribution
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
arXiv 2024
Giraffe: Adventures in Expanding Context Lengths in LLMs
arXiv 2023
from 2 papers
Arka Pal
Manley Roberts
Samuel Dooley
Siddartha Naidu
Arvind Sundararajan
researcher
Colin White