Update app.py

app.py

@@ -78,47 +78,110 @@ def get_model():
     #tokenizer = AutoTokenizer.from_pretrained("BigSalmon/DefinitionsSynonyms1")
     #model = AutoModelForCausalLM.from_pretrained("BigSalmon/DefinitionsSynonyms1")
 
-    tokenizer = AutoTokenizer.from_pretrained("BigSalmon/DefinitionsSynonyms2")
-    model = AutoModelForCausalLM.from_pretrained("BigSalmon/DefinitionsSynonyms2")
-    tokenizer2 = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincolnMedium")
-    model2 = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincolnMedium")
-    return model, model2, tokenizer, tokenizer2
+    tokenizer = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincoln95Paraphrase")
+    model = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincoln95Paraphrase")
+
+    #tokenizer = AutoTokenizer.from_pretrained("BigSalmon/DefinitionsSynonyms2")
+    #model = AutoModelForCausalLM.from_pretrained("BigSalmon/DefinitionsSynonyms2")
+    #tokenizer2 = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincolnMedium")
+    #model2 = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincolnMedium")
+    return model, tokenizer
     
-model, model2, tokenizer, tokenizer2 = get_model()
+model, tokenizer = get_model()
 
-st.text('''For Prompt Templates: https://huggingface.co/BigSalmon/InformalToFormalLincoln82Paraphrase''')
+g = """informal english: garage band has made people who know nothing about music good at creating music.
+Translated into the Style of Abraham Lincoln: garage band ( offers the uninitiated in music the ability to produce professional-quality compositions / catapults those for whom music is an uncharted art the ability the realize masterpieces / stimulates music novice's competency to yield sublime arrangements / begets individuals of rudimentary musical talent the proficiency to fashion elaborate suites ).
+informal english: chrome extensions can make doing regular tasks much easier to get done.
+Translated into the Style of Abraham Lincoln: chrome extensions ( yield the boon of time-saving convenience / ( expedite the ability to / unlock the means to more readily ) accomplish everyday tasks / turbocharges the velocity with which one can conduct their obligations ).
+informal english: broadband is finally expanding to rural areas, a great development that will thrust them into modern life.
+Translated into the Style of Abraham Lincoln: broadband is ( ( finally / at last / after years of delay ) arriving in remote locations / springing to life in far-flung outposts / inching into even the most backwater corners of the nation ) that will leap-frog them into the twenty-first century.
+informal english: google translate has made talking to people who do not share your language easier.
+Translated into the Style of Abraham Lincoln: google translate ( imparts communicability to individuals whose native tongue differs / mitigates the trials of communication across linguistic barriers / hastens the bridging of semantic boundaries / mollifies the complexity of multilingual communication / avails itself to the internationalization of discussion / flexes its muscles to abet intercultural conversation / calms the tides of linguistic divergence ).
+informal english: corn fields are all across illinois, visible once you leave chicago.
+Translated into the Style of Abraham Lincoln: corn fields ( permeate illinois / span the state of illinois / ( occupy / persist in ) all corners of illinois / line the horizon of illinois / envelop the landscape of illinois ), manifesting themselves visibly as one ventures beyond chicago.
+informal english: """
 
-temp = st.sidebar.slider("Temperature", 0.7, 1.5)
-number_of_outputs = st.sidebar.slider("Number of Outputs", 5, 50)
-lengths = st.sidebar.slider("Length", 3, 500)
-bad_words = st.text_input("Words You Do Not Want Generated", " core lemon height time ")
-logs_outputs = st.sidebar.slider("Logit Outputs", 50, 300)
+number_of_outputs = st.sidebar.slider("Number of Outputs", 5, 100)
+log_nums = st.sidebar.slider("How Many Log Outputs?", 50, 1000)
 
-def run_generate(text, bad_words):
-  yo = []
-  input_ids = tokenizer.encode(text, return_tensors='pt')
-  res = len(tokenizer.encode(text))
-  bad_words = bad_words.split()
-  bad_word_ids = []
-  for bad_word in bad_words: 
-    bad_word = " " + bad_word
-    ids = tokenizer(bad_word).input_ids
-    bad_word_ids.append(ids)
-  sample_outputs = model.generate(
-    input_ids,
-    do_sample=True, 
-    max_length= res + lengths, 
-    min_length = res + lengths, 
-    top_k=50,
-    temperature=temp,
-    num_return_sequences=number_of_outputs,
-    bad_words_ids=bad_word_ids
-  )
-  for i in range(number_of_outputs):
-    e = tokenizer.decode(sample_outputs[i])
-    e = e.replace(text, "")
-    yo.append(e)
-  return yo
+def BestProbs(prompt):
+  prompt = prompt.strip()
+  text = tokenizer.encode(prompt)
+  myinput, past_key_values = torch.tensor([text]), None
+  myinput = myinput
+  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(10)
+  best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]
+  for i in best_words[0:10]:
+    print("_______")
+    st.write(f"${i} $\n")
+    f = (f"${i} $\n")
+    m = (prompt + f"{i}")
+    BestProbs2(m)
+  return f
+
+def BestProbs2(prompt):
+  prompt = prompt.strip()
+  text = tokenizer.encode(prompt)
+  myinput, past_key_values = torch.tensor([text]), None
+  myinput = myinput
+  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(20)
+  best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]
+  for i in best_words[0:20]:
+    print(i)
+    st.write(i)
+    
+def LogProbs(prompt):
+  col1 = []
+  col2 = []
+  prompt = prompt.strip()
+  text = tokenizer.encode(prompt)
+  myinput, past_key_values = torch.tensor([text]), None
+  myinput = myinput
+  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(10)
+  best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]
+  for i in best_words[0:10]:
+    print("_______")
+    f = i
+    col1.append(f)
+    m = (prompt + f"{i}")
+    #print("^^" + f + " ^^")
+    prompt = m.strip()
+    text = tokenizer.encode(prompt)
+    myinput, past_key_values = torch.tensor([text]), None
+    myinput = myinput
+    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(20)
+    best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]
+    for i in best_words[0:20]:
+      #print(i)
+      col2.append(i)
+  #print(col1)
+  #print(col2)
+  d = {col1[0]: [col2[0], col2[1], col2[2], col2[3], col2[4], col2[5], col2[6], col2[7], col2[8], col2[9], col2[10], col2[11], col2[12], col2[13], col2[14], col2[15], col2[16], col2[17], col2[18], col2[19]],
+    col1[1]: [col2[20], col2[21], col2[22], col2[23], col2[24], col2[25], col2[26], col2[27], col2[28], col2[29], col2[30], col2[31], col2[32], col2[33], col2[34], col2[35], col2[36], col2[37], col2[38], col2[39]],
+    col1[2]: [col2[40], col2[41], col2[42], col2[43], col2[44], col2[45], col2[46], col2[47], col2[48], col2[49], col2[50], col2[51], col2[52], col2[53], col2[54], col2[55], col2[56], col2[57], col2[58], col2[59]],
+    col1[3]: [col2[60], col2[61], col2[62], col2[63], col2[64], col2[65], col2[66], col2[67], col2[68], col2[69], col2[70], col2[71], col2[72], col2[73], col2[74], col2[75], col2[76], col2[77], col2[78], col2[79]],
+    col1[4]: [col2[80], col2[81], col2[82], col2[83], col2[84], col2[85], col2[86], col2[87], col2[88], col2[89], col2[90], col2[91], col2[92], col2[93], col2[94], col2[95], col2[96], col2[97], col2[98], col2[99]],
+    col1[5]: [col2[100], col2[101], col2[102], col2[103], col2[104], col2[105], col2[106], col2[107], col2[108], col2[109], col2[110], col2[111], col2[112], col2[113], col2[114], col2[115], col2[116], col2[117], col2[118], col2[119]],
+    col1[6]: [col2[120], col2[121], col2[122], col2[123], col2[124], col2[125], col2[126], col2[127], col2[128], col2[129], col2[130], col2[131], col2[132], col2[133], col2[134], col2[135], col2[136], col2[137], col2[138], col2[139]],
+    col1[7]: [col2[140], col2[141], col2[142], col2[143], col2[144], col2[145], col2[146], col2[147], col2[148], col2[149], col2[150], col2[151], col2[152], col2[153], col2[154], col2[155], col2[156], col2[157], col2[158], col2[159]],
+    col1[8]: [col2[160], col2[161], col2[162], col2[163], col2[164], col2[165], col2[166], col2[167], col2[168], col2[169], col2[170], col2[171], col2[172], col2[173], col2[174], col2[175], col2[176], col2[177], col2[178], col2[179]],
+    col1[9]: [col2[180], col2[181], col2[182], col2[183], col2[184], col2[185], col2[186], col2[187], col2[188], col2[189], col2[190], col2[191], col2[192], col2[193], col2[194], col2[195], col2[196], col2[197], col2[198], col2[199]]}
+  df = pd.DataFrame(data=d)
+  print(df)
+  st.write(df)
+  return df
   
 def BestProbs5(prompt):
   prompt = prompt.strip()
@@ -137,88 +200,66 @@ def BestProbs5(prompt):
     st.write(g)
     l = run_generate(g, "hey")
     st.write(l)
-  
-def run_generate2(text, bad_words):
+    
+def run_generate(text, bad_words):
   yo = []
-  input_ids = tokenizer2.encode(text, return_tensors='pt')
-  res = len(tokenizer2.encode(text))
+  input_ids = tokenizer.encode(text, return_tensors='pt')
+  res = len(tokenizer.encode(text))
   bad_words = bad_words.split()
-  bad_word_ids = []
+  bad_word_ids = [[7829], [40940]]
   for bad_word in bad_words: 
     bad_word = " " + bad_word
-    ids = tokenizer2(bad_word).input_ids
+    ids = tokenizer(bad_word).input_ids
     bad_word_ids.append(ids)
-  sample_outputs = model2.generate(
+  sample_outputs = model.generate(
     input_ids,
     do_sample=True, 
-    max_length= res + lengths, 
-    min_length = res + lengths, 
+    max_length= res + 5, 
+    min_length = res + 5, 
     top_k=50,
-    temperature=temp,
-    num_return_sequences=number_of_outputs,
+    temperature=1.0,
+    num_return_sequences=3,
     bad_words_ids=bad_word_ids
   )
-  for i in range(number_of_outputs):
-    e = tokenizer2.decode(sample_outputs[i])
+  for i in range(3):
+    e = tokenizer.decode(sample_outputs[i])
     e = e.replace(text, "")
     yo.append(e)
+  print(yo)
   return yo
-  
-def prefix_format(sentence):
-  words = sentence.split()
-  if "[MASK]" in sentence:
-    words2 = words.index("[MASK]")
-    #print(words2)
-    output = ("<Prefix> " + ' '.join(words[:words2]) + " <Prefix> " + "<Suffix> " + ' '.join(words[words2+1:]) + " <Suffix>" + " <Middle>")
-    st.write(output)
-  else:
-    st.write("Add [MASK] to sentence")
- 
+
 with st.form(key='my_form'):
-    text = st.text_area(label='Enter sentence', value=first)
+    prompt = st.text_area(label='Enter sentence', value=g, height=500)
     submit_button = st.form_submit_button(label='Submit')
-    submit_button2 = st.form_submit_button(label='Submit Log Probs')
-    
-    submit_button3 = st.form_submit_button(label='Submit Other Model')
-    submit_button4 = st.form_submit_button(label='Submit Log Probs Other Model')
-    
-    submit_button5 = st.form_submit_button(label='Most Prob')
-    
-    submit_button6 = st.form_submit_button(label='Turn Sentence with [MASK] into <Prefix> Format')
-    
+    submit_button2 = st.form_submit_button(label='Fast Forward')
+    submit_button3 = st.form_submit_button(label='Fast Forward 2.0')
+    submit_button4 = st.form_submit_button(label='Get Top')
+
     if submit_button:
-      translated_text = run_generate(text, bad_words)
-      st.write(translated_text if translated_text else "No translation found")
-    if submit_button2:
       with torch.no_grad():
-        text2 = str(text)
-        print(text2)
-        text3 = tokenizer.encode(text2)
-        myinput, past_key_values = torch.tensor([text3]), None
+        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(logs_outputs)
-        best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]      
+        best_logits, best_indices = logits.topk(log_nums)
+        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)
+    if submit_button2:
+        print("----")
+        st.write("___")
+        m = LogProbs(prompt)
+        st.write("___")
+        st.write(m)
+        st.write("___")
     if submit_button3:
-      translated_text = run_generate2(text, bad_words)
-      st.write(translated_text if translated_text else "No translation found")
+        print("----")
+        st.write("___")
+        st.write(BestProbs)
     if submit_button4:
-      text2 = str(text)
-      print(text2)
-      text3 = tokenizer2.encode(text2)
-      myinput, past_key_values = torch.tensor([text3]), None
-      myinput = myinput
-      logits, past_key_values = model2(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(logs_outputs)
-      best_words = [tokenizer2.decode([idx.item()]) for idx in best_indices]      
-      st.write(best_words)
-    if submit_button5:
-      BestProbs5(text)
-    if submit_button6:
-      text2 = str(text)
-      prefix_format(text2)
+      BestProbs5(prompt)