📝 wip docs

hfdocs/source/index.mdx

@@ -1,10 +1,7 @@
 # timm
 
-`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts. It provides high-level APIs for popular model architectures and standard datasets, as well as utilities for low-level model manipulation.
+`timm` is a library containing SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations, and training/evaluation scripts.
 
-```python
+It comes packaged with >100 pretrained models, and is designed to be flexible and easy to use.
-import timm
 
-# Load a Pretrained Model
+Read the [quick start guide](quickstart) to get up and running with the `timm` library. You will learn how to load, discover, and use pretrained models included in the library.
-model = timm.create_model('resnet18', pretrained=True) 
-```