Add PyTorch Hub configuration file

[johnsutor]

This PR aims to add support for PyTorch's hub loading feature. This would make model loading as simple as specifying this git repo to download the CLIP model along with its pre-trained weights. When working with torch.hub.load, the example would change from this

import torch
import clip
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device)
text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device)

with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    
    logits_per_image, logits_per_text = model(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

print("Label probs:", probs)  # prints: [[0.9927937  0.00421068 0.00299572]]

to this

import torch
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = torch.hub.load("openai/CLIP", "ViT_B_32", device=device)
tokenize = torch.hub.load("openai/CLIP", "tokenize")

image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device)
text = tokenize(["a diagram", "a dog", "a cat"]).to(device)

with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    
    logits_per_image, logits_per_text = model(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

print("Label probs:", probs)  # prints: [[0.9927937  0.00421068 0.00299572]]

[jongwook]

It works! Thanks for the contribution :)