Add zipnn text

README.md

@@ -2,10 +2,60 @@
 tags:
 - vision
 widget:
-- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
+- src: >-
+    https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
   candidate_labels: playing music, playing sports
   example_title: Cat & Dog
+license: mit
+base_model:
+- openai/clip-vit-base-patch16
 ---
+# Disclaimer and Requirements
+
+This model is a clone of [**openai/clip-vit-base-patch32**](https://huggingface.co/openai/clip-vit-base-patch32) compressed using ZipNN. Compressed losslessly to 60% its original size, ZipNN saved ~0.3GB in storage and potentially ~9PB in data transfer **monthly**.
+
+### Requirement
+
+In order to use the model, ZipNN is necessary:
+```bash
+pip install zipnn
+```
+### Use This Model
+```python
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+from zipnn import zipnn_hf
+
+zipnn_hf()
+
+
+pipe = pipeline("zero-shot-image-classification", model="royleibov/clip-vit-base-patch16-ZipNN-Compressed")
+```
+```python
+# Load model directly
+from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
+from zipnn import zipnn_hf
+
+zipnn_hf()
+
+processor = AutoProcessor.from_pretrained("royleibov/clip-vit-base-patch16-ZipNN-Compressed")
+model = AutoModelForZeroShotImageClassification.from_pretrained("royleibov/clip-vit-base-patch16-ZipNN-Compressed")
+```
+### ZipNN
+ZipNN also allows you to seemlessly save local disk space in your cache after the model is downloaded.
+
+To compress the cached model, simply run:
+```bash
+python zipnn_compress_path.py bin --model royleibov/clip-vit-base-patch16-ZipNN-Compressed --hf_cache
+```
+
+The model will be decompressed automatically and safely as long as `zipnn_hf()` is added at the top of the file like in the [example above](#use-this-model).
+
+To decompress manualy, simply run:
+```bash
+python zipnn_decompress_path.py --model royleibov/clip-vit-base-patch16-ZipNN-Compressed --hf_cache
+```
+
 # Model Card: CLIP
 Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found [here](https://github.com/openai/CLIP/blob/main/model-card.md).
 
@@ -34,8 +84,12 @@ The original implementation had two variants: one using a ResNet image encoder a
 from PIL import Image
 import requests
 from transformers import CLIPProcessor, CLIPModel
-model = CLIPModel.from_pretrained("openai/clip-vit-base-patch16")
-processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch16")
+from zipnn import zipnn_hf
+
+zipnn_hf()
+
+model = CLIPModel.from_pretrained("royleibov/clip-vit-base-patch16-ZipNN-Compressed")
+processor = CLIPProcessor.from_pretrained("royleibov/clip-vit-base-patch16-ZipNN-Compressed")
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)
@@ -123,4 +177,4 @@ We also tested the performance of CLIP on gender, race and age classification us
 
 
 ### Where to send questions or comments about the model
-Please use [this Google Form](https://forms.gle/Uv7afRH5dvY34ZEs9)
+Please use [this Google Form](https://forms.gle/Uv7afRH5dvY34ZEs9)