Improve MoE implementation (#841)

This commit is contained in:
Sebastian Raschka
2025-09-22 15:21:06 -05:00
committed by GitHub
parent 20041fb94b
commit e742d8af2c
6 changed files with 177 additions and 250 deletions

1
.gitignore vendored
View File

@@ -83,6 +83,7 @@ gemma-3-270m-it/
Qwen3-0.6B-Base/
Qwen3-0.6B/
tokenizer-base.json
tokenizer-reasoning.json
tokenizer.json
# Datasets