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

- Made `NativeApi` into a `static class` (it's not intended to be instantiated)
 - Moved `LLamaTokenType` enum out into a separate file
 - Made `LLamaSeqId` and `LLamaPos` into `record struct`, convenient to have equality etc

- Passing `ILogger` into executors

# Conflicts:
#	LLama.Web/Common/ModelOptions.cs
#	LLama.Web/Services/ConnectionSessionService.cs
#	LLama/LLamaStatelessExecutor.cs
#	LLama/LLamaWeights.cs

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

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

- sealed some classes not intended to be extended

- Sanity checking that weights are not disposed when creating a context from them
 - Further simplified `Utils.InitLLamaContextFromModelParams`