bump version; update readme and changelog

README.md

@@ -174,6 +174,65 @@ _ = await chat.SendMessage("Lastly, give a thorough definition for a CS graduate
 chat.History.ForEach(c => Console.WriteLine($"{c.Role}: {c.Parts[0].Text}"));
 ```
 
+### Create a tuned model
+
+The Gemini API lets you tune models on your own data. Since it's your data and your tuned models this needs stricter access controls than API-Keys can provide.
+
+Before you can create a tuned model, you'll need to [setup OAuth for your project](https://ai.google.dev/palm_docs/oauth_quickstart).
+
+```csharp
+using Mscc.GenerativeAI;
+
+var projectId = "your_google_project_id"; // the ID of a project, not its name.
+var accessToken = "your_access_token";      // use `gcloud auth application-default print-access-token` to get it.
+var model = new GenerativeModel(apiKey: null, model: Model.Gemini10Pro001)
+{
+    AccessToken = accessToken,
+    ProjectId = projectId
+};
+var request = new CreateTunedModelRequest()
+{
+    BaseModel = $"models/{Model.Gemini10Pro001}",
+    DisplayName = "Autogenerated Test model",
+    TuningTask = new()
+    {
+        Hyperparameters = new() { BatchSize = 2, LearningRate = 0.001f, EpochCount = 3 },
+        TrainingData = new()
+        {
+            Examples = new()
+            {
+                Examples = new()
+                {
+                    new TrainingDataExample() { TextInput = "1", Output = "2" },
+                    new TrainingDataExample() { TextInput = "3", Output = "4" },
+                    new TrainingDataExample() { TextInput = "-3", Output = "-2" },
+                    new TrainingDataExample() { TextInput = "twenty two", Output = "twenty three" },
+                    new TrainingDataExample() { TextInput = "two hundred", Output = "two hundred one" },
+                    new TrainingDataExample() { TextInput = "ninety nine", Output = "one hundred" },
+                    new TrainingDataExample() { TextInput = "8", Output = "9" },
+                    new TrainingDataExample() { TextInput = "-98", Output = "-97" },
+                    new TrainingDataExample() { TextInput = "1,000", Output = "1,001" },
+                    new TrainingDataExample() { TextInput = "thirteen", Output = "fourteen" },
+                    new TrainingDataExample() { TextInput = "seven", Output = "eight" },
+                }
+            }
+        }
+    }
+};
+
+// Act
+var response = await model.CreateTunedModel(request);
+Console.WriteLine($"Name: {response.Name}");
+Console.WriteLine($"Model: {response.Metadata.TunedModel} (Steps: {response.Metadata.TotalSteps})");
+```
+(This is still work in progress but operational. Future release will provide types to simplify the create request.)
+
+Tuned models appear in your Google AI Studio library.
+
+[![Tuned models are listed below My Library in Google AI Studio](./docs/GeminiTunedModels.png)](https://aistudio.google.com/app/library)
+
+### More samples
+
 The folders [samples](./samples/) and [tests](./tests/) contain more examples.
 
 - [Simple console application](./samples/Console.Minimal.Prompt/)

src/Mscc.GenerativeAI.Google/CHANGELOG.md

@@ -11,6 +11,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 ### Fixed
 
+## 0.7.1
+
+### Changed
+
+- bump version
+
 ## 0.7.0
 
 ### Added

src/Mscc.GenerativeAI.Web/CHANGELOG.md

@@ -11,6 +11,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 ### Fixed
 
+## 0.7.1
+
+### Changed
+
+- bump version
+
 ## 0.5.1
 
 ### Changed

src/Mscc.GenerativeAI/CHANGELOG.md

@@ -8,9 +8,29 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Added
+
+- provide types to simplify creation of tuned model
+
 ### Changed
 ### Fixed
 
+## 0.7.1
+
+### Added
+
+- implement model tuning (works with stable models only)
+  - text-bison-001
+  - gemini-1.0-pro-001
+- tests for model tuning
+- 
+### Changed
+
+- improved authentication regarding API key or OAuth/ADC
+- added scope https://www.googleapis.com/auth/generative-language.tuning
+- harmonized version among NuGet packages
+- provide empty response on Safety stop
+- merged regular and tuned ModelResponse
+
 ## 0.7.0
 
 ### Added