Added conditional compilation code to progress_callback (in LlamaModelParams struct) so the struct plays nice with legacy NET Framework 4.8 (#593)

LLama/Native/LLamaModelParams.cs

@@ -27,13 +27,19 @@ namespace LLama.Native
         /// <summary>
         /// how to split layers across multiple GPUs (size: <see cref="NativeApi.llama_max_devices"/>)
         /// </summary>
-        public float* tensor_split;
-
+        public float* tensor_split;
+
         /// <summary>
         /// called with a progress value between 0 and 1, pass NULL to disable. If the provided progress_callback
         /// returns true, model loading continues. If it returns false, model loading is immediately aborted.
         /// </summary>
+#if NETSTANDARD2_0
+        // this code is intended to be used when running LlamaSharp on NET Framework 4.8 (NET Standard 2.0) 
+        // as NET Framework 4.8 does not play nice with the LlamaProgressCallback type
+        public IntPtr progress_callback;
+#else
         public LlamaProgressCallback progress_callback;
+#endif
 
         /// <summary>
         /// context pointer passed to the progress callback