Merge branch 'master' of https://github.com/SciSharp/LLamaSharp into upstream_master

.github/workflows/main.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        build: [linux-debug, linux-release, macos-debug, macos-release, windows-debug, windows-release]
+        build: [linux-debug, linux-release, windows-debug, windows-release]
         include:
           - build: linux-debug
             os: ubuntu-latest
@@ -20,12 +20,12 @@ jobs:
           - build: linux-release
             os: ubuntu-latest
             config: release
-          - build: macos-debug
-            os: macos-latest
-            config: debug
-          - build: macos-release
-            os: macos-latest
-            config: release
+          # - build: macos-debug
+          #   os: macos-latest
+          #   config: debug
+          # - build: macos-release
+          #   os: macos-latest
+          #   config: release
           - build: windows-debug
             os: windows-2019
             config: debug

LLama/Common/FixedSizeQueue.cs

@@ -30,8 +30,11 @@ namespace LLama.Common
         /// <param name="data"></param>
         public FixedSizeQueue(int size, IEnumerable<T> data)
         {
-#if NETCOREAPP3_0_OR_GREATER
-            // Try an early check on the amount of data supplied (if possible)
+#if NETSTANDARD2_0
+            var dataCount = data.Count();
+            if (data.Count() > size)
+                throw new ArgumentException($"The max size set for the quene is {size}, but got {dataCount} initial values.");
+#else
             if (data.TryGetNonEnumeratedCount(out var count) && count > size)
                 throw new ArgumentException($"The max size set for the quene is {size}, but got {count} initial values.");
 #endif
@@ -42,9 +45,12 @@ namespace LLama.Common
 
             // Now check if that list is a valid size
             if (_storage.Count > _maxSize)
-                throw new ArgumentException($"The max size set for the quene is {size}, but got {_storage.Count} initial values.");
+#if NETSTANDARD2_0
+                throw new ArgumentException($"The max size set for the quene is {size}, but got {dataCount} initial values.");
+#else
+                throw new ArgumentException($"The max size set for the quene is {size}, but got {count} initial values.");
+#endif
         }
-
         /// <summary>
         /// Replace every item in the queue with the given value
         /// </summary>

LLama/LLamaSharp.Runtime.targets

@@ -31,6 +31,10 @@
             <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
             <Link>libllama.dylib</Link>
         </None>
+        <None Include="$(MSBuildThisFileDirectory)runtimes/libllama-metal.dylib">
+            <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+            <Link>libllama-metal.dylib</Link>
+        </None>
         <None Include="$(MSBuildThisFileDirectory)runtimes/ggml-metal.metal">
             <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
             <Link>ggml-metal.metal</Link>

LLama/Native/NativeApi.cs

@@ -21,7 +21,8 @@ namespace LLama.Native
                     "1. No LLamaSharp backend was installed. Please search LLamaSharp.Backend and install one of them. \n" +
                     "2. You are using a device with only CPU but installed cuda backend. Please install cpu backend instead. \n" +
                     "3. The backend is not compatible with your system cuda environment. Please check and fix it. If the environment is " +
-                    "expected not to be changed, then consider build llama.cpp from source or submit an issue to LLamaSharp.");
+                    "expected not to be changed, then consider build llama.cpp from source or submit an issue to LLamaSharp.\n" + 
+                    "4. One of the dependency of the native library is missed.\n");
             }
             NativeApi.llama_backend_init(false);
         }

README.md

@@ -49,7 +49,7 @@ Here's the mapping of them and corresponding model samples provided by `LLamaSha
 | v0.2.2 | v0.2.2, v0.2.3 | [WizardLM](https://huggingface.co/TheBloke/wizardLM-7B-GGML/tree/previous_llama_ggmlv2), [Vicuna (filenames without "old")](https://huggingface.co/eachadea/ggml-vicuna-13b-1.1/tree/main) | 63d2046 |
 | v0.3.0, v0.3.1 | v0.3.0, v0.4.0 | [LLamaSharpSamples v0.3.0](https://huggingface.co/AsakusaRinne/LLamaSharpSamples/tree/v0.3.0), [WizardLM](https://huggingface.co/TheBloke/wizardLM-7B-GGML/tree/main) | 7e4ea5b |
 | v0.4.1-preview (cpu only) | v0.4.1-preview | [Open llama 3b](https://huggingface.co/SlyEcho/open_llama_3b_ggml), [Open Buddy](https://huggingface.co/OpenBuddy/openbuddy-llama-ggml)| aacdbd4 |
-| v0.4.2-preview (cpu,cuda11) |v0.4.2-preview | [Llama2 7b](https://huggingface.co/TheBloke/llama-2-7B-Guanaco-QLoRA-GGML)| - |
+| v0.4.2-preview (cpu,cuda11) |v0.4.2-preview | [Llama2 7b](https://huggingface.co/TheBloke/llama-2-7B-Guanaco-QLoRA-GGML)| 332311234a0aa2974b2450710e22e09d90dd6b0b |
 
 Many hands make light work. If you have found any other model resource that could work for a version, we'll appreciate it for opening an PR about it! 😊
 
@@ -148,7 +148,7 @@ Since we are in short of hands, if you're familiar with ASP.NET core, we'll appr
 
 ⚠️ BotSharp Integration
 
-⚠️ ASP.NET core Integration
+✅ ASP.NET core Integration
 
 ⚠️ Semantic-kernel Integration