- `AntipromptProcessor` accepts chunks of text and returns a value indicating if any antiprompt has been detected.
 - `StreamingTokenDecoder` decodes tokens into text, maintaining some internal state to handle single characters which are encoded as multiple tokens.

Added tests for these classes and updated StatelessExecutor to use them.

Removed most DeTokenize methods, marked the rest as obsolete (should always use a `StreamingTokenDecoder`).

- Built a new (hacky) `Detokenize` method which handles this

- Replaced all binaries

- Minimal amount of characters converted
   - Allocation free
 - Added `TokensToSpan` to `SafeLlamaModelHandle` which converts as many tokens as possible into a character span
   - Allocation free

Based on this version: 6b73ef1201

- Just convert it to a `string`, nice and simple
 - Write the bytes to a `Span<byte>` no allocations
 - Write the chars to a `StringBuilder` potentially no allocations

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

- sealed some classes not intended to be extended

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

- Added disposal check into `SafeLLamaContextHandle`

- 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.