File size: 1,010 Bytes
1a8c724
4d3d295
 
 
 
 
1a8c724
 
4d3d295
 
 
 
 
 
 
 
 
 
 
 
 
1a8c724
 
 
e9e5a55
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
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("google/mt5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("./models/checkpoint-15000/")


def text_processing(text):
    inputs = [text]

    # Tokenize and prepare the inputs for model
    input_ids = tokenizer(inputs, return_tensors="pt", max_length=512, truncation=True, padding="max_length").input_ids.to(device)
    attention_mask = tokenizer(inputs, return_tensors="pt", max_length=512, truncation=True, padding="max_length").attention_mask.to(device)

    # Generate prediction
    output = model.generate(input_ids=input_ids, attention_mask=attention_mask, max_new_tokens=512)

    # Decode the prediction
    decoded_output = [tokenizer.decode(ids, skip_special_tokens=True) for ids in output]

    return decoded_output[0]

iface = gr.Interface(fn = text_processing, inputs='text', outputs=['text'], title='test', description='test space')

iface.launch(inline=False)