Update README.md

README.md

@@ -22,14 +22,13 @@ pipeline_tag: text-generation
 **Orchestrix** is a fine-tuned **FunctionGemma 270M** model designed for **on-device UI orchestration** using **function calling**.  
 It converts natural language commands into **deterministic UI actions**, running fully **offline** via MediaPipe.
 
-
 ## Model Description
 
 This is a fine-tuned version of **FunctionGemma 270M Instruct** specifically trained for natural language-based UI control through function calling. The model interprets user commands and generates structured function calls to manipulate application UI elements.
 
 **Base Model**: `google/functiongemma-270m-it`  
 **Fine-tuning Task**: Function calling for UI control  
-**Format**: MediaPipe Task file (`.task`)  
+**Format**: MediaPipe compatible formats (`.task`, `.tflite`, `.litert`)  
 **Deployment**: On-device inference via Flutter
 
 ## Intended Use
@@ -43,38 +42,40 @@ This is a fine-tuned version of **FunctionGemma 270M Instruct** specifically tra
 
 ### Supported Functions
 
-The model is trained to call the following functions:
+The model is trained to call the following 6 functions:
 
 | Function | Description | Parameters |
 |----------|-------------|------------|
-| `change_theme` | Switch app theme | `theme`: "light", "dark", or "system" |
-| `change_background_color` | Modify background color | `color`: "red", "blue", "green", "black", "white", "yellow", "purple", "orange" |
-| `change_text_color` | Change text color | `color`: "white" or "black" |
-| `change_text_size` | Adjust text size | `size`: "small", "medium", or "large" |
+| `change_theme` | Switch app theme | `theme`: "light", "dark", "system", "blue", "green", "purple", "orange", "red", "material", "cupertino", "custom" |
+| `change_background_color` | Modify background color | `color`: "red", "green", "blue", "yellow", "purple", "orange", "white", "black", "pink", "cyan", "amber", "teal", "indigo", "lime", "brown", "grey" |
+| `change_text_color` | Change text color | `color`: "red", "green", "blue", "yellow", "purple", "orange", "white", "black", "pink", "cyan", "amber", "teal", "indigo", "lime", "brown", "grey" |
+| `change_text_size` | Adjust text size | `size`: "small", "medium", "large", "extra large", "tiny", "12", "14", "16", "18", "20", "22", "24", "28", "32", "36", "40", "48" |
+| `change_app_title` | Change application title | `title`: Any app name (200+ variations including "Dashboard", "Settings", "Task Manager", etc.) |
+| `show_alert` | Display notification/alert | `title`: Alert title, `message`: Alert message |
 
 ## Training Details
 
 ### Training Data
 
-The model was fine-tuned on a custom dataset of ~1000 examples mapping natural language commands to function calls. Training data format:
+The model was fine-tuned on a custom dataset of **3,300 examples** mapping natural language commands to function calls. The dataset was synthetically generated with diverse phrasing patterns to ensure robust understanding.
+
+**Training data statistics**:
+- **Total examples**: 3,300
+- **Functions**: 6 (change_theme, change_background_color, change_text_color, change_text_size, change_app_title, show_alert)
+- **Pattern variations**: 10-12 unique phrasings per function
+- **Color options**: 16 colors
+- **Theme options**: 11 themes
+- **Text size options**: 17 size variations
+- **App titles**: 200+ predefined titles
+- **Alert variations**: 100+ titles and 150+ messages
+
+Training data format (JSONL):
 
 ```json
 {
-  "messages": [
-    {
-      "role": "user",
-      "content": "Make the background blue"
-    },
-    {
-      "role": "assistant",
-      "tool_calls": [
-        {
-          "name": "change_background_color",
-          "arguments": {"color": "blue"}
-        }
-      ]
-    }
-  ]
+  "user_content": "make the background purple",
+  "tool_name": "change_background_color",
+  "tool_arguments": "{\"color\": \"purple\"}"
 }
 ```
 
@@ -82,10 +83,10 @@ The model was fine-tuned on a custom dataset of ~1000 examples mapping natural l
 
 - **Base Model**: FunctionGemma 270M Instruct
 - **Fine-tuning Method**: Supervised fine-tuning on function calling examples
-- **Training Examples**: ~1000 user command → function call pairs
+- **Training Examples**: 3,300 user command → function call pairs
+- **Data Generation**: Synthetic data with template-based variation
 - **Optimization**: Focused on accurate function name and parameter extraction
 
-
 ## Usage
 
 ### Flutter Integration
@@ -96,8 +97,6 @@ import 'package:flutter_gemma/flutter_gemma.dart';
 // Initialize Flutter Gemma
 await FlutterGemma.initialize();
 
-// Install the model
-
 // Create model instance
 final model = await FlutterGemma.getActiveModel(
   maxTokens: 1024,
@@ -114,13 +113,93 @@ final tools = [
       'properties': {
         'theme': {
           'type': 'string',
-          'enum': ['light', 'dark', 'system'],
+          'enum': ['light', 'dark', 'system', 'blue', 'green', 'purple', 
+                   'orange', 'red', 'material', 'cupertino', 'custom'],
         },
       },
       'required': ['theme'],
     },
   ),
-  // ... other tools
+  Tool(
+    name: 'change_background_color',
+    description: 'Change the background color of the app',
+    parameters: {
+      'type': 'object',
+      'properties': {
+        'color': {
+          'type': 'string',
+          'enum': ['red', 'green', 'blue', 'yellow', 'purple', 'orange', 
+                   'white', 'black', 'pink', 'cyan', 'amber', 'teal', 
+                   'indigo', 'lime', 'brown', 'grey'],
+        },
+      },
+      'required': ['color'],
+    },
+  ),
+  Tool(
+    name: 'change_text_color',
+    description: 'Change the text color in the app',
+    parameters: {
+      'type': 'object',
+      'properties': {
+        'color': {
+          'type': 'string',
+          'enum': ['red', 'green', 'blue', 'yellow', 'purple', 'orange', 
+                   'white', 'black', 'pink', 'cyan', 'amber', 'teal', 
+                   'indigo', 'lime', 'brown', 'grey'],
+        },
+      },
+      'required': ['color'],
+    },
+  ),
+  Tool(
+    name: 'change_text_size',
+    description: 'Adjust the text size',
+    parameters: {
+      'type': 'object',
+      'properties': {
+        'size': {
+          'type': 'string',
+          'enum': ['small', 'medium', 'large', 'extra large', 'tiny', 
+                   '12', '14', '16', '18', '20', '22', '24', '28', 
+                   '32', '36', '40', '48'],
+        },
+      },
+      'required': ['size'],
+    },
+  ),
+  Tool(
+    name: 'change_app_title',
+    description: 'Change the application title',
+    parameters: {
+      'type': 'object',
+      'properties': {
+        'title': {
+          'type': 'string',
+          'description': 'The new title for the application',
+        },
+      },
+      'required': ['title'],
+    },
+  ),
+  Tool(
+    name: 'show_alert',
+    description: 'Display an alert or notification',
+    parameters: {
+      'type': 'object',
+      'properties': {
+        'title': {
+          'type': 'string',
+          'description': 'The alert title',
+        },
+        'message': {
+          'type': 'string',
+          'description': 'The alert message',
+        },
+      },
+      'required': ['title', 'message'],
+    },
+  ),
 ];
 
 // Create chat session
@@ -146,9 +225,9 @@ Model Output: {
 }
 ```
 
-**Example 2: Color Change**
+**Example 2: Background Color**
 ```
-User: "Make the background purple"
+User: "make it purple"
 Model Output: {
   "tool_calls": [{
     "name": "change_background_color",
@@ -157,36 +236,64 @@ Model Output: {
 }
 ```
 
-**Example 3: Multiple Commands**
+**Example 3: Text Styling**
 ```
-User: "Change to dark theme and make text large"
+User: "make text large and cyan"
 Model Output: {
   "tool_calls": [
-    {
-      "name": "change_theme",
-      "arguments": {"theme": "dark"}
-    },
     {
       "name": "change_text_size",
       "arguments": {"size": "large"}
+    },
+    {
+      "name": "change_text_color",
+      "arguments": {"color": "cyan"}
     }
   ]
 }
 ```
 
+**Example 4: App Title**
+```
+User: "rename app to Task Manager"
+Model Output: {
+  "tool_calls": [{
+    "name": "change_app_title",
+    "arguments": {"title": "Task Manager"}
+  }]
+}
+```
+
+**Example 5: Alert Notification**
+```
+User: "show alert Success with message File uploaded successfully"
+Model Output: {
+  "tool_calls": [{
+    "name": "show_alert",
+    "arguments": {
+      "title": "Success",
+      "message": "File uploaded successfully"
+    }
+  }]
+}
+```
+
+
 ## Limitations
 
-1. **Limited Function Set**: Only supports 4 predefined functions
-2. **Parameter Constraints**: Parameters are restricted to predefined enums
+1. **Limited Function Set**: Only supports 6 predefined functions
+2. **Parameter Constraints**: Colors and themes are restricted to predefined enums
 3. **Language**: English only
 4. **Context**: Optimized for UI control tasks, not general conversation
-5. **Ambiguity**: May struggle with highly ambiguous or complex commands
+5. **Ambiguity**: May struggle with highly ambiguous commands not seen during training
+6. **Synthetic Training**: Trained on template-generated data, may differ from real user phrasing
 
 ## Bias and Ethical Considerations
 
 - The model is trained on synthetic data and may not represent diverse user populations
 - Function calling is deterministic and limited to safe UI operations
 - No personal data is collected or transmitted (fully on-device)
+- Color names follow Western conventions and may not align with all cultural interpretations
 
 ## Model Card Authors
 
@@ -205,3 +312,10 @@ This model is released under the [Gemma License](https://ai.google.dev/gemma/ter
 - **Google DeepMind** for the Gemma base model
 - **MediaPipe** for on-device inference capabilities
 - **Flutter Gemma** package maintainers
+
+## Repository
+
+Training scripts and dataset generation code available in the project repository:
+- `generate_data.py`: Synthetic dataset generation script
+- `training_data.jsonl`: 3,300 training examples
+- `train.jsonl`: Converted training data for fine-tuning