Update app.py

app.py

@@ -13,10 +13,10 @@ st.markdown('''
 
 Hi! This is the demo for the [flax sentence embeddings](https://huggingface.co/flax-sentence-embeddings) created for the **Flax/JAX community week 🤗**. 
 We trained three general-purpose flax-sentence-embeddings models: a **distilroberta base**, a **mpnet base** and a **minilm-l6**. 
-All were trained on all the datasets of the [1B+ train corpus](https://huggingface.co/flax-sentence-embeddings/all_datasets_v4_MiniLM-L6#training-data) with the v3 setup.
+The models were trained on a dataset comprising of [1 Billion+ training corpus](https://huggingface.co/flax-sentence-embeddings/all_datasets_v4_MiniLM-L6#training-data) with the v3 setup.
 
 In addition, we trained [20 models](https://huggingface.co/flax-sentence-embeddings) focused on general-purpose, QuestionAnswering and Code search.
-View our models [here](https://huggingface.co/flax-sentence-embeddings)
+You can view our models [here](https://huggingface.co/flax-sentence-embeddings)
 
 To evaluate the [flax-sentence-embeddings](https://huggingface.co/flax-sentence-embeddings) *Sentence Similarity models* for *Gender Bias based on stereotypical occupations*, we created an *evaluation set* which can be found [here](https://huggingface.co/datasets/manandey/Gender_Bias_Evaluation)
 
@@ -63,8 +63,8 @@ For more cool information on sentence embeddings, see the [sBert project](https:
 elif menu == "Asymmetric QA":
     st.header('Asymmetric QA')
     st.markdown('''
-**Instructions**: You can compare the Answer likeliness of a given Query with answer candidates of your choice. In the background, we'll create an embedding for each answers, and then we'll use the cosine similarity function to calculate a similarity metric between our query sentence and the others.
-`mpnet_asymmetric_qa` model works best for hard negative answers or distinguishing similar queries due to separate models applied for encoding questions and answers.
+**Instructions**: You can compare the Answer likeliness of a given Query with answer candidates of your choice. In the background, we'll create an embedding for each answer, and then we'll use the cosine similarity function to calculate a similarity metric between our query sentence and the others.
+`mpnet_asymmetric_qa` model works best for hard-negative answers or distinguishing similar queries due to separate models applied for encoding questions and answers.
 
 For more cool information on sentence embeddings, see the [sBert project](https://www.sbert.net/examples/applications/computing-embeddings/README.html).
 ''')