Please use portrait mode

Rotate your device to continue.

RepoVerseBack to archive
Common

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

ATK
2657
DEF
2132

turboderp/exllama

Common · Base · Genesis

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Attack2,657
Defense2,132

Drag the card to turn it. Use the flip button to see the back.

View on GitHub
Open card page