Move README section

README.md

@@ -31,10 +31,6 @@ The weights shared here correspond to our best-performing model, COLIPRI-CRM.
 COLIPRI is shared for research purposes only.
 It is **not meant to be used for clinical practice**.
 
-<!-- ### Downstream use -->
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
 The encoders be plugged to other models, or used independently or jointly for many downstream tasks, such as:
 
 - Image classification with text prompts
@@ -51,24 +47,15 @@ The encoders be plugged to other models, or used independently or jointly for ma
 
 Fine-tuning COLIPRI is typically not necessary to obtain good performance in downstream tasks.
 
-<!-- ### Out-of-scope use -->
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-## Biases, risks, and limitations
+## Getting started
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-COLIPRI was trained with data from Turkey and the USA only, therefore it might be biased towards population in the training data.
-Underlying biases of the training datasets may not be well characterized.
-
-## Installation
+### Installation
 
 ```shell
 pip install git+https://huggingface.co/microsoft/colipri.git
 ```
 
-## Usage examples
+### Usage examples
 
 Below we share some usage snippets to get started with COLIPRI.
 A more complete [Jupyter notebook](./COLIPRI_demo.ipynb) is also available.
@@ -96,7 +83,7 @@ Now, let's instantiate the model and processor.
 >>> processor = get_processor()
 ```
 
-### Zero-shot classification
+#### Zero-shot classification
 
 ```python
 >>> from colipri import ZeroShotImageClassificationPipeline
@@ -108,7 +95,7 @@ Now, let's instantiate the model and processor.
 ]
 ```
 
-### Feature extraction
+#### Feature extraction
 
 ```python
 >>> import torch
@@ -128,6 +115,13 @@ torch.Size([1, 768, 24, 24, 24])
 torch.Size([1, 768])
 ```
 
+## Biases, risks, and limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+COLIPRI was trained with data from Turkey and the USA only, therefore it might be biased towards population in the training data.
+Underlying biases of the training datasets may not be well characterized.
+
 ## Environmental impact
 
 <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
@@ -149,7 +143,7 @@ COLIPRI was trained on [Azure Machine Learning](https://azure.microsoft.com/en-u
 | Stage | Node type | Num. nodes | GPU type | GPUs per node |
 | --- | --- | --- | --- | --- |
 | Pre-training | [`Standard_NC96ads_A100_v4`](https://learn.microsoft.com/en-us/azure/virtual-machines/sizes/gpu-accelerated/nca100v4-series?tabs=sizeaccelerators) | 1 | NVIDIA A100 (80 GB) | 4 |
-| Evaluation   | [`Standard_NC24ads_A100_v4`](https://learn.microsoft.com/en-us/azure/virtual-machines/sizes/gpu-accelerated/nca100v4-series?tabs=sizeaccelerators) | 1 | NVIDIA A100 (80 GB) | 1 |
+| Evaluation | [`Standard_NC24ads_A100_v4`](https://learn.microsoft.com/en-us/azure/virtual-machines/sizes/gpu-accelerated/nca100v4-series?tabs=sizeaccelerators) | 1 | NVIDIA A100 (80 GB) | 1 |
 
 #### Software