README.md in onnxruntime-0.2.1 vs README.md in onnxruntime-0.2.2

@@ -48,16 +48,59 @@
 
 ```ruby
 model.predict({x: [1, 2, 3]}, output_names: ["label"])
 ```
 
+## Session Options
+
+```ruby
+OnnxRuntime::Model.new(path_or_bytes, {
+  enable_cpu_mem_arena: true,
+  enable_mem_pattern: true,
+  enable_profiling: false,
+  execution_mode: :sequential,
+  graph_optimization_level: nil,
+  inter_op_num_threads: nil,
+  intra_op_num_threads: nil,
+  log_severity_level: 2,
+  log_verbosity_level: 0,
+  logid: nil,
+  optimized_model_filepath: nil
+})
+```
+
+## Run Options
+
+```ruby
+model.predict(input_feed, {
+  log_severity_level: 2,
+  log_verbosity_level: 0,
+  logid: nil,
+  terminate: false
+})
+```
+
 ## Inference Session API
 
 You can also use the Inference Session API, which follows the [Python API](https://microsoft.github.io/onnxruntime/python/api_summary.html).
 
 ```ruby
 session = OnnxRuntime::InferenceSession.new("model.onnx")
 session.run(nil, {x: [1, 2, 3]})
+```
+
+The Python example models are included as well.
+
+```ruby
+OnnxRuntime::Datasets.example("sigmoid.onnx")
+```
+
+## GPU Support
+
+To enable GPU support on Linux and Windows, download the appropriate [GPU release](https://github.com/microsoft/onnxruntime/releases) and set:
+
+```ruby
+OnnxRuntime.ffi_lib = "path/to/lib/libonnxruntime.so" # onnxruntime.dll for Windows
 ```
 
 ## History
 
 View the [changelog](https://github.com/ankane/onnxruntime/blob/master/CHANGELOG.md)