File size: 1,826 Bytes
c6eaf06 eb91b0e c6eaf06 |
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 |
import streamlit as st
import transformers
from transformers import AutoTokenizer, AutoModelWithLMHead
model_name = "orzhan/rut5-base-detox"
tokenizer = AutoTokenizer.from_pretrained(model_name)
@st.cache
def load_model(model_name):
model = AutoModelWithLMHead.from_pretrained(model_name)
return model
model = load_model(model_name)
def infer(input_ids):
output_sequences = model.generate(
input_ids=input_ids,
max_length=60,
do_sample=False,
num_return_sequences=1,
num_beams=32,
length_penalty=2.0,
no_repeat_ngram_size=4
)
return output_sequences
default_value = "А ну иди сюда, придурок"
#prompts
st.title("Дело детоксификации на ruT5")
sent = st.text_area("Text", default_value, height = 275)
encoded_prompt = tokenizer.encode(sent, add_special_tokens=False, return_tensors="pt")
if encoded_prompt.size()[-1] == 0:
input_ids = None
else:
input_ids = encoded_prompt
output_sequences = infer(input_ids)
for generated_sequence_idx, generated_sequence in enumerate(output_sequences):
print(f"=== GENERATED SEQUENCE {generated_sequence_idx + 1} ===")
generated_sequences = generated_sequence.tolist()
# Decode text
text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)
# Remove all text after the stop token
#text = text[: text.find(args.stop_token) if args.stop_token else None]
# Add the prompt at the beginning of the sequence. Remove the excess text that was used for pre-processing
total_sequence = (
sent + text[len(tokenizer.decode(encoded_prompt[0], clean_up_tokenization_spaces=True)) :]
)
generated_sequences.append(total_sequence)
print(total_sequence)
st.write(generated_sequences[-1])
|