Skip to content
This repository was archived by the owner on Jul 18, 2025. It is now read-only.

Commit 810d372

Browse files
authored
Merge pull request #46 from ARM-software/transformer-tutorials
Added transformers quantization guide
2 parents 8595dc6 + f62636d commit 810d372

File tree

7 files changed

+6652
-0
lines changed

7 files changed

+6652
-0
lines changed
Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
# Transformer Tutorials
2+
3+
Jupiter notebooks showing how to quantise and compress toy transformer encoder and encoder-decoder models.
4+
5+
# Tutorials
6+
7+
* ViT_PCQAT.ipynb - Shows PCQAT using TFMOT for transformer encoder models.
8+
* ViT_2x4-PQAT.ipynb - Shows new 2x4 pruning and QAT with TFMOT for transformer encoder models.
9+
* translation.ipynb - Shows how to do QAT with TFMOT for encoder-decoder models.
10+
* translation_PQAT.ipynb - Shows how to apply pruning & QAT with TFMOT for encoder-decoder models.

0 commit comments

Comments
 (0)