Update README.md

README.md

@@ -8,6 +8,8 @@ tags:
 
 This repo contains all the required Learnable Weight Clipping for Omniquant https://arxiv.org/abs/2308.13137. 
 
+# How to use it?
+
 To use them please first run:
 
 ```
@@ -26,4 +28,8 @@ CUDA_VISIBLE_DEVICES=0 python OmniQuant/main.py \
 --epochs 0 --output_dir ./log/test \
 --eval_ppl --wbits 4 --abits 16 --group_size 128 --lwc \
 --resume OmniQuant_LWC/NAME_OF_MODEL-w4a16g128.pth
-```
+```
+
+# Methodology
+
+The weights were run using a fork of OmniQuant available at [calibration.ipynb](https://github.com/Tfloow/AndaQuant/blob/main/calibration.ipynb)