- Added disposal check into `SafeLLamaContextHandle`

- Also refactored it to return an `int[]` instead of an `IEnumerable<int>`, solving the "multiple enumeration" problems at the source!

feat: update the llama backends.

It solves the problem with netstandard2 (is it really netstandard2 a thing right now?)
Change context to solve problems.

5f631c2679

Fixed Memory pinning in Sampling API

- 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`

- Additional comments

This change _only_ implements the low level API and makes no effort to update the LlamaSharp higher level abstraction.

It is built upon llama `b3f138d`, necessary DLLs are **not** included in this commit.

Memory Mapped LoadState/SaveState

XML docs fixes

- 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.

Adapt the interface change in llama_backend_init