Add application file

app.py

@@ -9,8 +9,48 @@ import numpy as np
 import streamlit as st
 st.title('Code Generation')
 huggingface_dataset_name = "red1xe/code_instructions"
+if st.button("Load Dataset"):
+    with st.spinner('Loading Dataset...'):
+        dataset = load_dataset(huggingface_dataset_name)
 
-dataset = load_dataset(huggingface_dataset_name)
+if st.button("Show Dataset"):
+    st.write(dataset)
 
-st.write("## Dataset")
-st.write(dataset)
+if st.button("Load Model"):
+    with st.spinner('Loading Model...'):
+        model_name='google/flan-t5-base'
+        original_model = AutoModelForSeq2SeqLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
+        tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+x = st.slider('Select a sample', 0, 1000, 200)
+if st.button("Show Sample"):
+    index = x
+
+    input = dataset['test'][index]['input']
+    instruction = dataset['test'][index]['instruction']
+    output = dataset['test'][index]['output']
+
+    prompt = f"""
+    Answer the following question.
+
+    {input} {instruction}
+
+    Answer:
+    """
+
+    inputs = tokenizer(prompt, return_tensors='pt')
+    outputs = tokenizer.decode(
+        original_model.generate(
+            inputs["input_ids"],
+            max_new_tokens=200,
+        )[0],
+        skip_special_tokens=True
+    )
+
+    dash_line = '-'.join('' for x in range(100))
+    st.write(dash_line)
+    st.write(f'INPUT PROMPT:\n{prompt}')
+    st.write(dash_line)
+    st.write(f'BASELINE HUMAN SUMMARY:\n{output}\n')
+    st.write(dash_line)
+    st.write(f'MODEL GENERATION - ZERO SHOT:\n{outputs}')