Update README.md

README.md

@@ -5,6 +5,58 @@ datasets:
 - TokenBender/code_instructions_122k_alpaca_style
 metrics:
 - accuracy
+language:
+- en
+widget:
+  - text: |
+      ### Instruction: write a neural network complete code in Keras 
+      ### Input: Use cifar dataset 
+      ### Response:
+  
+    output:
+      text: >-
+        from keras.datasets import cifar10
+        import numpy as np
+        from keras.models import Sequential
+        from keras.layers import Dense, Dropout, Activation, Flatten
+        from keras.layers import Conv2D, MaxPooling2D
+        from keras.utils import to_categorical
+        from keras.optimizers import Adam
+        
+        # Load the CIFAR-10 dataset
+        (X_train, y_train), (X_test, y_test) = cifar10.load_data()
+        
+        # Normalize pixel values to be between 0 and 1
+        X_train = X_train.astype('float32') / 255
+        X_test = X_test.astype('float32') / 255
+        
+        # Convert class vectors to binary class matrices
+        y_train = to_categorical(y_train, num_classes=10)
+        y_test = to_categorical(y_test, num_classes=10)
+        
+        # Create the model
+        model = Sequential()
+        model.add(Conv2D(32, (3, 3), input_shape=(32, 32, 3)))
+        model.add(Activation('relu'))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+        
+        model.add(Conv2D(64, (3, 3)))
+        model.add(Activation('relu'))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+        
+        model.add(Flatten())
+        model.add(Dense(64))
+        model.add(Activation('relu'))
+        model.add(Dropout(0.5))
+        model.add(Dense(10))
+        model.add(Activation('softmax'))
+        
+        # Compile the model
+        model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
+        
+        # Train the model
+        model.fit(X_train, y_train, batch_size=32, epochs=10, validation_split=0.2)
+  
 pipeline_tag: text-generation
 base_model: codellama/CodeLlama-13b-Instruct-hf
 ---