Update tg.ggml

tg.ggml

@@ -11,7 +11,7 @@ model MyModel {
 
   // Embedding layer
   embeddings {
-    dim: 64;
+    dim: 128;
   }
 
   // Encoder layers
@@ -19,13 +19,20 @@ model MyModel {
     type: lstm;
     units: 128;
     num_layers: 2;
+    dropout: 0.2;  // Add dropout for regularization
   }
 
   // Decoder layers
   decoder {
     type: gru;
     units: 64;
-    num_layers: 1;
+    num_layers: 2;
+    dropout: 0.1;  // Add dropout for regularization
+  }
+
+  // Attention mechanism
+  attention {
+    type: scaled_dot_product;
   }
 
   // Output layer
@@ -46,9 +53,14 @@ model MyModel {
   }
 }
 
-// Training parameters
-train {
-  // ... (Define training data and hyperparameters)
+// Training parameters (in train.json)
+{
+  "data_path": "path/to/your/training_data.txt",
+  "batch_size": 32,
+  "epochs": 10,
+  "use_scheduled_sampling": true,  // Enable scheduled sampling
+  "clip_gradients": 5.0,  // Add gradient clipping to prevent exploding gradients
+  "use_batch_norm": true  // Enable batch normalization
 }
 
 // Inference parameters