Optim-wip: Add the CLIP ResNet 50x4 model

[ProGamerGov]

• Added the CLIP ResNet 50x4 model used in the 'Multimodal Neurons in Artificial Neural Networks' research paper: https://distill.pub/2021/multimodal-neurons/
• To make it easier to conduct research, the CLIP ResNet 50x4 model is divided into two parts; the image model and the text model.

I have a couple tutorials ready that use this model. I also have another PR ready that implements the tokenizer for the text model, using torchtext's CLIPTokenizer.

[ProGamerGov]

The CLIP PRs are: #927, #943, #945, #961, #965, #966, #968