Generate python

from transformers import AutoTokenizer, AutoModelWithLMHead


tokenizer = AutoTokenizer.from_pretrained("Sentdex/GPyT")
model = AutoModelWithLMHead.from_pretrained("Sentdex/GPyT").to("cuda")


def generate(code, max_length=100):
    '''Takes input code, replaces newline chars with <N>, 
    tokenizes, feeds thru model, decodes, 
    then reformats the newlines back in'''
    newlinechar = "<N>"
    converted = code.replace("\n", newlinechar)
    tokenized = tokenizer.encode(converted, return_tensors='pt').to("cuda")
    resp = model.generate(tokenized, max_length=max_length).to("cuda")

    decoded = tokenizer.decode(resp[0])
    reformatted = decoded.replace("<N>","\n")
    return reformatted


print(generate("import"))

Source: pythonprogramming.net

Similar codes

0 vote311 views1 answer
Change value in excel in python
Python
1 vote315 views1 answer
How to loop back to try except python
Python
0 vote341 views1 answer
Python scatter plot legend
Python
0 vote316 views1 answer
How to delete all item in treeview tkinter
Python
1 vote349 views1 answer
Write a Python program to read last n lines of a file
Python
1 vote370 views2 answers
Python extraer ultimo elemento lista
Python
0 vote317 views1 answer
Python map string to int
Python
2 votes391 views2 answers
Django filter and condition
Python Django
0 vote347 views1 answer
Python pie chart with legend
Python
1 vote324 views1 answer
Module 'tensorflow_core.compat.v1.random' has no attribute 'set_seed'
Python