amd-shark
/

sdxl-quant-int8

Model card Files Files and versions

Update quant params structure

#2

by nickfraser - opened Jun 28, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

Feat (math model/tests): Updated math model and tests to match use format1b07a9de

AMD SHARK org Jun 28, 2024

•

edited Jul 3, 2024

Updates the following:

Add <weight|input>_zp_dtype to quant_param.json to differentiate between exported versions
Update input/weight zero-points to be int8 (not uint8)
Update the math model and tests to incorporate the above changes
Remove SmoothQuant multipliers from layers that aren't quantized
~~Upload new quant_param.json~~
~~Upload new params.safetensors~~
~~Upload new example output out.safetensors~~
~~Confirm compliant FID of model (FID ∈ (23.0108, 23.9501)): 23.89~~
~~Confirm compliant CLIP score of model (CLIP ∈ (31.686, 31.813)): 31.86~~

~~Strikethrough~~ items were updated outside this PR.

nickfraser changed pull request status to open Jul 3, 2024

nickfraser changed pull request status to merged Jul 3, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment