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

10 votes199 views2 answers
How to find length of number in python
Python
0 vote197 views1 answer
Numpy index array all except
Python
1 vote225 views2 answers
Download pdf from url python
Python
1 vote205 views1 answer
Seaborn plot set ylabel
Python
0 vote196 views1 answer
Find closest color python
Python
16 votes221 views2 answers
Access row of dataframe
Python
7 votes231 views2 answers
Ckeditor django
Python
12 votes250 views6 answers
How to print string in python
Python
0 vote196 views1 answer
Why wont my python input accept string inputs
Python
103 votes192 views6 answers
Rename df column
Python