Add GGUF support

- 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

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.

Based on this version: 6b73ef1201

ModelsParams record class

- Used those methods to add a `Clone` method to SafeLLamaContextHandle
 - Simplified `LLamaContext` by using the new methods
 - Sealed `LLamaContext` and `LLamaEmbedder`

- Equality, hashing etc all implemented automatically
 - Default values are defined in just one place (the properties) instead of the constructor as well
 - Added test to ensure that serialization works properly

- Deleted `NativeInfo` (internal class, not used anywhere)

- Passing encoding in the `IModelParams`, which reduces how often encoding needs to be passed around

- Removed some unnecessary `ToArray` calls
 - Initial pass on LLamaStatelessExecutor, the context overflow management is broken but I think I found where it's ported from

- Integrated grammar into sampling
 - Added a test for the grammar sampling

The biggest single change is renaming `LLamaModel` to `LLamaContext`

- Caching that folder, so CI only has to download it once.

The poc of the test is working know. Finally the problem error seems to be related with the process stopping.
Once I changed the context with today llama.cpp binaries is working OK