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 vote139 views2 answers
Print font size python
Python
0 vote128 views1 answer
Empty argument as a parameter in python function using None
Python
7 votes120 views6 answers
Venv
Python
3 votes132 views6 answers
Fizz buzz python
Python
1 vote126 views1 answer
Handler.setLevel(logging.DEBUG) not working python
Python
6 votes140 views1 answer
Python soap
Python
0 vote224 views1 answer
AssertionError: Relational field must provide a `queryset` argument, override `get_queryset`, or set read_only=`True`
Python
9 votes124 views3 answers
How to join tables in python
Python
1 vote134 views1 answer
How to make a blank window open up in python
Python
7 votes130 views4 answers
Pandas filter rows by value
Python