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 vote238 views1 answer
Open a python script on click flask
Python
19 votes251 views5 answers
Python floor
Python
1 vote249 views1 answer
How to pick out separate columns from the pandas dataframe object
Python
5 votes255 views2 answers
Regular expression to remove space python
Python
2 votes233 views2 answers
Install python3.7 ubuntu 20.04
Python
0 vote236 views1 answer
Colorbar remove tick lines and border
Python
0 vote247 views1 answer
Increase pie chart size python
Python
1 vote229 views2 answers
Python pd.DataFrame.from_records remove header
Python
12 votes234 views5 answers
Remove special characters from string in python
Python
1 vote235 views1 answer
Argparse boolean default
Python