Add the Quantized model and also a Demo of the Quantized model

[Ruhaan838]

Post Training Quantization for GPT2

• In this commit, I try to add the Quantization for the GPT2 most of the code remains the same.
• Made the new files quantized_model.py in this repo I tried my best for this.
• If anything you feel is wrong then ask me I try my best.
• I can't change the original code just make the new file and done.

Size measure for both models

• Original GPT2 (from_pretrain): 497813.01 KB
• Quantized GPT2 (from_pretrain): 164120.94 KB
• Difference: 333692.07 KB

Drawbacks

• I still can't figure out how to generate the text with this Quantized model.
• After applying the engine for quantization it will show the error of NotImplementation for Embeddings

@karpathy If you have time to review this code and merge it or feel something wrong then tell me I try my best