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 vote200 views1 answer
Lose your django secret key
Python
0 vote174 views2 answers
Ip regex python
Python
0 vote176 views1 answer
Uppy tus
Python
1 vote198 views1 answer
How to install pandas datareader in conda
Python
2 votes186 views1 answer
Version of scikit learn
Python
0 vote222 views1 answer
Python yield from
Python
2 votes234 views2 answers
Python "for in" loop to print the last item in the list
Python
0 vote217 views1 answer
Median absolute deviation scipy
Python
0 vote174 views1 answer
Jpg image in tkinter title
Python
3 votes190 views1 answer
How to write to a file in python without deleting all content
Python