Update app.py

app.py

@@ -1,4 +1,67 @@
 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])
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)