A 14B model trained on high-quality synthetic data plus post-training steps surpasses GPT-4 on STEM QA benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
UNVERDICTED 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Phi-4 Technical Report
A 14B model trained on high-quality synthetic data plus post-training steps surpasses GPT-4 on STEM QA benchmarks.