Add decoding capability to GPT2BPE tokenizer

[reachsumit]

Description

Add add_special_tokens feature to GPT2BPETokenizer

This change is targeted towards a requirement posted internally. It adds a new function add_special_tokens to GPT2BPETokenizer in order to enable the user to specify a dictionary of token that should not be changed during tokenization. Any newly specified token shall also be added to the vocabulary.

The change adds the capability to decode tokens ids back to text. This change is required following the internal discussion.

Types of changes

[x ] New feature (non-breaking change which adds core functionality)

Changes made

• Made changes to C++ code (GPT2BPEEncoder class) to support the decode functionality.
• Updated torch bindings and py bindings as required.
• Added decode function to Python interface (GPT2BPETokenizer class).
• Added unit test to test the decoding process.

Testing

• No issue identified in pre-commit
• No issue identified with any of the unit tests.

[joecummings]

This looks good to me. Thanks for getting this up so quickly. cc @Nayef211 for another approval.

[Nayef211]

LGTM!