Add TextEmbedding for Semantic Kernel

Swapped to llama-7b-chat

Removed duplicate `llama_sample_classifier_free_guidance` method

Disable test parallelism

refactor: remove old version files.

Remove LLamaNewlineTokens from InteractiveExecutorState

* Restore macOS pipelines
* Generate Metal binaries.

The D is for my middle name 😄

docs: update the docs to follow new version.

Add GGUF support

grammar_exception_types

Enable Semantic kernel support

Changes to compile in VS Mac + change model to llama2

Higher Level Grammar System

- Made all the mechanics of grammar parsing (GBNFGrammarParser, ParseState) internal. Just call `Grammar.Parse("whatever")`.
 - Added a `GrammarRule` class which validates elements on construction (this allows constructing grammar without parsing GBNF).
   - It should be impossible for a `GrammarRule` to represent an invalid rule.

This commit includes changes to compile en VS Mac + changest to use llama2 not codellama.

It includes MacOS binaries in memory and metal

Translating the grammar parser

SymbolIds is now SortedDictionary (although I'm not sure it really needs to be) because the test was failing due to expected value being in another order. The C++ data structure if SymbolIds is std::map<std::string, uint32_t> so the items are ordered by key.