Update README.md

README.md

@@ -1,17 +1,25 @@
-
 ---
-library_name: keras
+license: mit
+tags:
+- keras
+- mnist
+- classification
+- digits
 ---
 
-This model has been uploaded using the Keras library and can be used with JAX,
-TensorFlow, and PyTorch backends.
+# PracticheskayaCK
+
+Эта модель обучена распознавать рукописные цифры 0, 5 и 9 из набора данных MNIST.
+
+## Архитектура
+
+- Входной слой: `Flatten(input_shape=(28, 28, 1))`
+- Скрытый слой: `Dense(128, activation='relu')`
+- Выходной слой: `Dense(3, activation='softmax')`
 
-This model card has been generated automatically and should be completed by the
-model author.
-See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for
-more information.
+## Использование
 
-For more details about the model architecture, check out
-[config.json](./config.json).
+```python
+import keras
 
-![](./assets/summary_plot.png)
+model = keras.saving.load_model("hf://eyescry/PracticheskayaCK")