- Moved repeated code to convert `LLamaTokenDataArray` into a `LLamaTokenDataArrayNative` into a helper method.
   - Modified all call sites to dispose the `MemoryHandle`
 - Saved one copy of the `List<LLamaTokenData>` into a `LLamaTokenData[]` in `LlamaModel`

Instruct & Stateless web example implemented

Larger states

Memory Mapped LoadState/SaveState

Cleaned up unnecessary extension methods

XML docs fixes

Documentation Spelling/Grammar

fix breaking change in llama.cpp; bind to latest version llama.cpp to…

Basic ASP.NET Core website example

MacOS metal support

- A C# array cannot exceed 2,147,483,591 bytes. In my own use of LlamaSharp I encountered this limit.
 - This saves an extra copy of the entire state data into a C# `byte[]`, so it should be faster.

This does _not_ fix some other places where `GetStateData` is used. I'll look at those in a separate PR.

- Renamed `DictionaryExtensions` to `KeyValuePairExtensions`, since nothing in that file extends dictionary any more!

Keep update binaries

Adapt the interface change in llama_backend_init

Update with all new changes

update webapi example

Add metal libraries and ggml-metal.metal helper

Update libllama.dylib

Align llama.cpp MacOS Dynamic Link Library

Remove native libraries from LLama.csproj and replace it with a targets file.