update app

app.py

@@ -3,7 +3,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
 from transformers import pipeline
 import torch
 import json
-
+import pandas as pd
 
 @st.cache(allow_output_mutation=True)
 def load_tokenizer(model_ckpt):
@@ -59,16 +59,19 @@ set_seed(42)
 gen_kwargs = {}
 
 if selected_task == " ":
-    st.title("Code Generation Models comparison 💻")
+    st.title("Code Generation Models comparison")
     with open("intro.txt", "r") as f:
         intro = f.read()
     st.markdown(intro)
 elif selected_task == "Pretraining dataset":
     st.title("Pretraining datasets 📚")
+    st.Markdown("Preview of some code files from Github repositories")   
+    df = pd.read_csv("preview-github-data.csv")
+    st.dataframe(df)
     for model in selected_models:
         with open(f"datasets/{model.lower()}.txt", "r") as f:
             text = f.read()
-        st.markdown(f"## {model}:")
+        st.markdown(f"### {model}:")
         st.markdown(text)   
 elif selected_task == "Model architecture":
     st.title("Model architecture 🔨")