Interface administrators, Administrators (Semantic MediaWiki), Curators (Semantic MediaWiki), Editors (Semantic MediaWiki), Suppressors, Administrators
7,785
edits
LLaMA/Model Card: Difference between revisions
→Quantitative analysis
No edit summary |
|||
| Line 48: | Line 48: | ||
{| class="wikitable" | {| class="wikitable" | ||
|- | |||
|+ style="caption-side:bottom"|Table 1 - Summary of LLama Model Hyperparameters | |||
|- | |- | ||
! colspan="1"| LLaMa | ! colspan="1"| LLaMa | ||
! colspan="6"| Model hyper parameters | ! colspan="6"| Model hyper parameters | ||
|- | |- | ||
! | !# of parameters | ||
!dimension | !dimension | ||
!n heads | !n heads | ||
| Line 69: | Line 71: | ||
|- | |- | ||
|} | |} | ||
We present our results on eight standard common sense reasoning benchmarks in the table below. | We present our results on eight standard common sense reasoning benchmarks in the table below. | ||