- 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

- Fixed stateless executor out-of-context handling
 - Fixed token tests

- params contains a list of loras, instead of just one

This commit includes changes to compile en VS Mac + changest to use llama2 not codellama.

It includes MacOS binaries in memory and metal

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

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