transformers
c06d4cd6 - Add EXAONE 4.0 model (#39129)

Commit
213 days ago
Add EXAONE 4.0 model (#39129) * Add EXAONE 4.0 model * Refactor EXAONE 4.0 modeling code * Fix cache slicing on SWA + FA2 * Fix cache slicing on FA2 + HybridCache * Update EXAONE 4.0 modeling code for main branch * Update o_proj for asymmetric projection * Address PR feedback * Add EXAONE 4.0 docs * Update EXAONE 4.0 modeling code for main branch * update * fix updates * updates * fix * fix * fix --------- Co-authored-by: Arthur <arthur.zucker@gmail.com> Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Author
Parents
Loading