Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import os
+import torch
+import torch.nn as nn
+from transformers import ElectraModel, AutoConfig, GPT2LMHeadModel
+from transformers.activations import get_activation
+from transformers import AutoTokenizer
+
+
+st.title('Informal to Formal')
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+st.text('''How To Make Prompt:
+
+informal english: space is huge and needs to be explored.
+Translated into the Style of Abraham Lincoln: space awaits traversal, a new world whose boundaries are endless.
+Translated into the Style of Abraham Lincoln: space is a boundless expanse, a vast virgin domain awaiting exploration.
+
+informal english: i am very ready to do that just that.
+Translated into the Style of Abraham Lincoln: you can assure yourself of my readiness to work toward this end.
+Translated into the Style of Abraham Lincoln: please be assured that i am most ready to undertake this laborious task.
+
+informal english: meteors are much harder to see, because they are only there for a fraction of a second.
+Translated into the Style of Abraham Lincoln: meteors are not readily detectable, lasting for mere fractions of a second.
+
+informal english:''')
+
+
+from transformers import AutoTokenizer, AutoModelWithLMHead
+tokenizer = AutoTokenizer.from_pretrained("gpt2")
+model = AutoModelWithLMHead.from_pretrained("BigSalmon/MrLincoln3")
+
+with st.form(key='my_form'):
+    prompt = st.text_area(label='Enter sentence')
+    submit_button = st.form_submit_button(label='Submit')
+
+    if submit_button:
+      with torch.no_grad():
+        text = tokenizer.encode(prompt)
+        myinput, past_key_values = torch.tensor([text]), None
+        myinput = myinput
+        myinput= myinput.to(device)
+        logits, past_key_values = model(myinput, past_key_values = past_key_values, return_dict=False)
+        logits = logits[0,-1]
+        probabilities = torch.nn.functional.softmax(logits)
+        best_logits, best_indices = logits.topk(60)
+        best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]
+        text.append(best_indices[0].item())
+        best_probabilities = probabilities[best_indices].tolist()
+        words = []              
+        st.write(best_words)