The original message contained the word "preceeded" which should be spelled as "preceded"

Introduced a new `BatchedExecutor`

- Re-implmented `Rewind` as an extension method using `Modify` internally
 - Implemented `ShiftLeft`, which shifts everything over except for some starting tokens. This is the same as the `StatelessExecutor` out-of-context handling.
 - Starting batch at epoch 1, this ensures that conversations (starting at zero) are below the current epoch. It also means `0` can always be used as a value guaranteed to be below the current epoch.

Conversations can be "forked", to create a copy of a conversation at a given point. This allows e.g. prompting a conversation with a system prefix just once and then forking it again and again for each individual conversation. Conversations can also be "rewound" to an earlier state.

Added two new examples, demonstrating forking and rewinding.

Small KV Cache Handling Improvements

- Added `KvCacheSequenceDivide`
 - Moved count tokens/cells methods to `SafeLLamaContextHandle`

Update binaries feb 2024

- Modified `GetEmbeddings` method to be async

Removed `SafeLLamaHandleBase` Constructor

- Also fixed `ToString()` in `SafeLLamaHandleBase`

This results in windows users not needing to rename the DLL. This allows native llama builds to be dropped in, even on windows.

I also took the time to update the documentation, removing references to renaming the files, since the names now match.

Fixes #463

Bumps [System.Text.Json](https://github.com/dotnet/runtime) from 8.0.0 to 8.0.1.
- [Release notes](https://github.com/dotnet/runtime/releases)
- [Commits](https://github.com/dotnet/runtime/compare/v8.0.0...v8.0.1)

---
updated-dependencies:
- dependency-name: System.Text.Json
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Swapped `StatelessExecutor` to use `llama_decode`!

- Growing more than double, if necessary

- Added `logits_i` argument to `Context.ApplyPenalty`
 - Added a new exception type for `llama_decode` return code

- using less `NativeHandle`
 - Using `StreamingTokenDecoder` instead of obsolete detokenize method

- Added a `DecodeAsync` overload which runs the work in a task
 - Replaced some `NativeHandle` usage in `BatchedDecoding` with higher level equivalents.
 - Made the `LLamaBatch` grow when token capacity is exceeded, removing the need to manage token capacity externally.

Model Metadata Loading Cleanup

- Clarified comments on native metadata loading methods

- Checking if model is readable

Added a check for EOS token in LLamaStatelessExecutor

- Properly displaying `LLamaToken`
 - Removed all tokenisation code in `SafeLLamaContextHandle` - just pass it all through to the `SafeLlamaModelHandle`
 - Improved `SafeLlamaModelHandle` tokenisation:
   - Renting an array, for one less allocation
   - Not using `&tokens[0]` to take a pointer to an array, this is redundant and doesn't work on empty arrays

LLamaToken Struct