transformers
Fix DBRX MoE hidden size and expert GLU transposes
#47671
Merged

Commits
  • Fix DBRX MoE hidden size and expert GLU transposes
    kaixuanliu committed 10 days ago
  • update
    kaixuanliu committed 7 days ago
  • propogate self.d_model to ffn_config.hidden_size
    kaixuanliu committed 7 days ago
  • update
    kaixuanliu committed 6 days ago
  • update
    kaixuanliu committed 6 days ago
  • update comment
    kaixuanliu committed 6 days ago
Loading