.Net: cl100k_base tokenizer

[anthonypuppo]

The existing GPT3Tokenizer class uses p50k_base encoding. GPT-3.5, GPT-4, and text-embedding-ada-002 all rely on cl100k_base encoding.

The below table is extracted from the OpenAI notebook on token counting.

Encoding name	OpenAI models
cl100k_base	gpt-4, gpt-3.5-turbo, text-embedding-ada-002
p50k_base	Codex models, text-davinci-002, text-davinci-003
r50k_base (or gpt2)	GPT-3 models like davinci

[anthonypuppo]

SharpToken

[nacharya1]

@dluc are you able to look into this?