update readme in ga_squad

examples/trials/ga_squad/readme.md → examples/trials/ga_squad/README.md

+# Automaticlly model architecture search for Reading Comprehension
+SQuAD is a competition holded by Stanford. Giving you queries and passages, you need to select answer from passage.
+
+This example shows us how to use Genetic Algorithm to find good model architectures for Reading Comprehension task.
+
+Since attention and recurrent neural network (RNN) module have been proven effective in Reading Comprehension.
+
+We conclude the search space as follow:
+
+1. IDENTITY (Effectively means keep training).
+2. INSERT-RNN-LAYER (Inserts a LSTM. Comparing the performance of GRU and LSTM in our experiment, we decided to use LSTM here.)
+3. REMOVE-RNN-LAYER
+4. INSERT-ATTENTION-LAYER(Inserts a attention layer.)
+5. REMOVE-ATTENTION-LAYER
+6. ADD-SKIP (Identity between random layers).
+7. REMOVE-SKIP (Removes random skip).
+
+
+![ga-squad-logo](./ga_squad.png)
+
+Also we have another version which time cost is less and performance is better. We will release soon.
+
+
 # Download data
 
 ## Use downloading script
@@ -27,7 +50,6 @@ unzip glove.840B.300d.zip
 ```
 
 # How to submit this job
-
-1. run "$NNI_ROOT_DIR/auto_run.py" as "$NNI_ROOT_DIR/README-AUTO.md" said.
-2. use the dockerImage openpai.azurecr.io/nni_v0.0.1, which means it use a tensorflow cpu-version.
-3. this model don't need search_space.json.
\ No newline at end of file
+```
+nnictl create --config ~/nni/examples/trials/ga_squad/config.yaml
+```