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 vote643 views1 answer
Python string: .title()
Python
0 vote121 views1 answer
Obspy stats
Python
3 votes128 views1 answer
Maping value to data in pandas dataframe
Python
21 votes114 views2 answers
Jupyter notebook warning off
Python
4 votes134 views10 answers
Roblox
Python
0 vote84 views1 answer
Keyboard input raspberry pi
Python
0 vote127 views1 answer
Regrid ntdcf file usig xarray
Python
0 vote136 views1 answer
Detect gender from name
Python
-1 vote114 views2 answers
Write a python program to multiplies all the items in a list.
Python
-1 vote149 views1 answer
Django email verification
Python Django