File size: 2,440 Bytes
aab6c14 2d62d9e 8510d8c aab6c14 6dcec7c aab6c14 6dcec7c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
import openai
import streamlit as st
from transformers import AutoTokenizer
import pandas as pd
import numpy as np
@st.cache(allow_output_mutation=True)
def get_model():
tokenizer = AutoTokenizer.from_pretrained("gpt2")
return tokenizer
tokenizer = get_model()
number_of_probs = st.slider("Length", 5, 99)
temp = st.slider('Temperature', 0.7, 5.0, 1.0)
tokens = st.slider('Length', 3, 25, 20)
def run_generate(bad_words):
bad_words = bad_words.split()
bad_word_ids = []
for bad_word in bad_words:
bad_word = " " + bad_word
ids = tokenizer(bad_word).input_ids
ids = str(ids)
ids = ids.replace("]", ": -30").replace("[", "").replace(", ", ":-30, ")
bad_word_ids.append(ids)
bad_word_ids = str(bad_word_ids)
bad_word_ids = bad_word_ids.replace("['", "{").replace("']", "}").replace("'", "")
bad_word_ids = bad_word_ids + ","
print(bad_word_ids)
return bad_word_ids
with st.form(key='my_form'):
prompt = st.text_area(label='Enter sentence', value=" ")
bad_words = st.text_area("Words You Do Not Want Generated", " core lemon height time ")
key = st.text_area("Key", " core lemon height time ")
openai.api_key = key
bad_words = run_generate(bad_words)
yes =eval(bad_words)
bad_wordss = (yes[0])
submit_button = st.form_submit_button(label='Submit')
submit_button2 = st.form_submit_button(label='Submit Log Probs')
if submit_button:
response = openai.Completion.create(engine="code-davinci-002", prompt=prompt, temperature=temp, max_tokens=tokens, top_p=0.8, n=50,
logit_bias = bad_wordss,)
st.write(response)
if submit_button2:
response = openai.Completion.create(engine="code-davinci-002", prompt=prompt + " ", top_p=0.1, logprobs=number_of_probs, max_tokens=1, logit_bias = bad_wordss,)
scores = pd.DataFrame([response["choices"][0]["logprobs"]["top_logprobs"][0]]).T
scores.columns = ["logprob"]
scores["%"] = scores["logprob"].apply(lambda x: 100*np.e**x)
g = scores.sort_values(by="%", ascending=False)
first_column = g.iloc[:, 0]
okay = first_column.to_string()
h = []
for i in range(len(okay)):
try:
if okay[i] == "-":
okay = okay[0:i] + okay[i+9:]
h.append(okay)
except:
pass
words2 = (h[-1])
words = words2.split()
st.write(words)
#words2 = words2 + " "
#print("---")
#print(prompt + words2)
#print("---")
#st.write(words2) |