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

28 votes265 views5 answers
Python style console output
Python
0 vote275 views1 answer
Open pkl file python
Python
0 vote296 views1 answer
Python add datetime to filename
Python
0 vote301 views1 answer
Python Multiline docstring example
Python
1 vote315 views5 answers
How to install django in virtual environment in ubuntu
Python Django
0 vote282 views1 answer
Which env im running jupyter notebook
Python
0 vote295 views1 answer
Determine how 2 string si equal py
Python
1 vote280 views1 answer
Python get object class
Python
0 vote275 views1 answer
Python3 array
Python
0 vote235 views1 answer
Scipy.arange is deprecated and will be removed
Python