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

- Converted `SafeLLamaContextHandle` to take a `ReadOnlySpan` for Eval, narrower type better represents what's really needed

- sealed some classes not intended to be extended

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

- 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!

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.