A 13B model called Orca learns detailed reasoning from GPT-4 explanation traces and reaches parity with ChatGPT on Big-Bench Hard while outperforming other 13B models.
The false promise of imitating proprietary llms, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
A 13B model called Orca learns detailed reasoning from GPT-4 explanation traces and reaches parity with ChatGPT on Big-Bench Hard while outperforming other 13B models.